Concevoir, développer et optimiser des modèles d’apprentissage automatique qui alimentent les décisions fondées sur les données

Le rôle
Nous sommes à la recherche d’un ingénieur en apprentissage automatique pour se joindre à une équipe collaborative qui livre des solutions avancées d’analytique et d’IA dans le secteur des services financiers. Ce rôle met l’accent sur le cycle de vie complet des modèles d’apprentissage automatique — de la développement et l’expérimentation au déploiement, à la surveillance et à l’amélioration continue — ainsi que sur l’application de techniques d’IA générative.

Ce que vous ferez

• Concevoir, développer et maintenir des modèles d’apprentissage automatique pour résoudre des problèmes d’affaires critiques
• Assumer des responsabilités clés dans le cycle de vie des modèles, notamment l’ingénierie des caractéristiques, l’ajustement, l’évaluation et la calibration
• Appliquer l’analytique prédictive et des techniques de conception de requêtes pour extraire des insights à partir de jeux de données complexes
• Effectuer des tests de modèles, des benchmarks et un suivi continu de la performance
• Collaborer avec les parties prenantes pour traduire les besoins d’affaires en solutions d’AA évolutives

Ce que nous recherchons

• Plus de 5 ans d’expérience dans des rôles en apprentissage automatique ou en science des données
• Excellentes compétences en développement Python avec expérience pratique de la création de modèles d’AA
• Solide compréhension des concepts d’apprentissage automatique, du cycle de vie des modèles et des meilleures pratiques
• Expérience avec les grands modèles de langage (LLM), l’IA générative et la conception de requêtes
• Solides compétences analytiques et en communication, avec la capacité de travailler auprès des équipes techniques et d’affaires

Atouts

• Expérience en gestion de patrimoine ou dans les services financiers (souhaitée, mais non obligatoire)
• Connaissance du déploiement, de la surveillance et du réentraînement de modèles en environnements de production
• Expérience avec des plateformes d’AA infonuagiques ou des solutions de données évolutives
• Expérience avec des outils d’automatisation ou d’optimisation des flux de travail
• Expérience de travail au sein d’équipes agiles ou interfonctionnelles
• Maîtrise du français et de l’anglais
• Étant donné que la majorité de nos clients et collègues sont situés à l’extérieur du Québec et du Canada, des exigences linguistiques particulières peuvent s’appliquer et une maîtrise professionnelle de l’anglais est requise.

Pourquoi joindre Capco

• Livrer des solutions technologiques à fort impact pour des institutions financières de premier ordre
• Travailler dans une culture de consultation collaborative, horizontale et entrepreneuriale
• Accéder à de la formation continue, du perfectionnement et à des certifications reconnues dans l’industrie
• Faire partie d’une équipe qui façonne l’avenir des services financiers numériques
• Contribuez à façonner l’avenir de la transformation numérique dans les secteurs des services financiers et de l’énergie

Nous offrons un régime d’avantages sociaux concurrentiel et axé sur les personnes, conçu pour soutenir tous les aspects de votre vie :

Avantages

• Couverture d’avantages complète – assurance santé, vie et invalidité entièrement payée par l’entreprise, en vigueur dès le premier jour d’emploi
• Programme d’épargne-retraite – Régime enregistré d’épargne-retraite (REER) avec option de cotisation de l’employeur
• Soins de santé virtuels – Programme payé par l’entreprise pour les employés et leurs personnes à charge
• Programme d’aide aux employés et à leur famille (PAEF) – Services de soutien confidentiels
• Soutien au mieux-être – Remboursement d’activités de mise en forme pour soutenir le bien-être

Transparence salariale

La fourchette salariale pour ce poste est indiquée ci-dessous. De plus, ce poste peut également être admissible à un paiement annuel de prime discrétionnaire/variable.

Capco s'engage à offrir une rémunération juste et équitable à son personnel. Nos politiques de rémunération et nos fourchettes salariales sont conçues pour permettre à nos employés de progresser dans la fourchette salariale à mesure qu'ils démontrent de solides performances et se développent dans leur rôle au fil du temps. Le salaire de base offert aux candidats retenus sera conforme à la fourchette salariale, et le placement variera en fonction de divers facteurs, y compris, mais sans s'y limiter, les connaissances, compétences, expérience et équité interne liées au poste.

CAD $118000 - CAD $152000

Utilisation de l’intelligence artificielle dans l’acquisition de talents
Chez Capco, nous utilisons des outils d’intelligence artificielle (IA) pour appuyer et améliorer plusieurs aspects de l’acquisition de talents. Cela comprend l’utilisation de fonctionnalités alimentées par l’IA dans LinkedIn pour aider à repérer des candidats potentiels, l’accélération des communications de recrutement courantes comme les courriels et la création d’offres d’emploi convaincantes, alignées sur la marque et reflétant fidèlement les exigences du poste, ainsi que des applications de planification par IA pour améliorer l’efficacité de la coordination des entrevues.
L’IA est utilisée uniquement comme outil d’appui. Toutes les décisions d’embauche sont prises par les équipes d’acquisition de talents et de recrutement.

Pourquoi ce poste est ouvert
Nous recrutons actuellement pour ce poste en raison d’un poste vacant existant ou nouvellement créé au sein de notre organisation. Ce poste est ouvert dans le cadre de nos besoins d’affaires continus, et nous examinons activement les candidatures afin de pourvoir ce rôle avec une personne qualifiée qui pourra avoir un impact immédiat.

Inclusion chez Capco
Nous nous engageons à rendre notre processus de recrutement accessible et simple pour tout le monde. Si vous avez besoin d’aménagements à n’importe quelle étape, faites-le-nous savoir — nous serons heureux de vous aider. Nous valorisons la perspective et la contribution uniques de chaque personne. Chez Capco, nous croyons qu’être soi-même est votre plus grande force. Notre culture #BeYourselfAtWork encourage l’individualité et la collaboration — un état d’esprit qui façonne notre façon de travailler avec nos clients et entre nous, chaque jour.

Chez Capco, nous utilisons des outils d’intelligence artificielle (IA) pour appuyer et améliorer plusieurs aspects de l’acquisition de talents. Cela comprend l’utilisation de fonctionnalités alimentées par l’IA dans LinkedIn pour aider à repérer des candidats potentiels, l’accélération des communications de recrutement courantes comme les courriels et la création d’offres d’emploi convaincantes, alignées sur la marque et reflétant fidèlement les exigences du poste, ainsi que des applications de planification par IA pour améliorer l’efficacité de la coordination des entrevues.
L’IA est utilisée uniquement comme outil d’appui. Toutes les décisions d’embauche sont prises par les équipes d’acquisition de talents et de recrutement.

Design, build, and optimize machine learning models that power data-driven decisions

The Role
We are seeking a Machine Learning Engineer to join a collaborative team delivering advanced analytics and AI solutions within financial services. This role focuses on the full lifecycle of machine learning models—from development and experimentation to deployment, monitoring, and continuous improvement—alongside the application of generative AI techniques.

What You’ll Do

• Design, develop, and maintain machine learning models to solve business-critical problems
• Own key aspects of the model lifecycle including feature engineering, tuning, evaluation, and calibration
• Apply predictive analytics and prompt engineering techniques to extract insights from complex datasets
• Perform model testing, benchmarking, and ongoing performance monitoring
• Collaborate with stakeholders to translate business requirements into scalable ML solutions

What We’re Looking For

• 5+ years of experience in machine learning or data science roles
• Proficient Python development skills with hands-on experience building ML models
• Strong understanding of machine learning concepts, model lifecycle, and best practices
• Experience with large language models (LLMs), generative AI, and prompt engineering
• Solid analytical and communication skills, with the ability to work across technical and business teams

Bonus Points For

• Experience in wealth management or financial services (preferred but not required)
• Familiarity with model deployment, monitoring, and retraining in production environments
• Experience with cloud-based ML platforms or scalable data solutions
• Exposure to workflow automation or optimization tools
• Experience working in agile or cross-functional teams
• Proficiency in French and English
• Given the majority of our clients and colleagues are located outside of Quebec and Canada, specific language requirements may apply and professional proficiency in English is required.

Why Join Capco

• Deliver high-impact technology solutions for Tier 1 financial institutions
• Work in a collaborative, flat, and entrepreneurial consulting culture
• Access continuous learning, training, and industry certifications
• Be part of a team shaping the future of digital financial services
• Help shape the future of digital transformation across FS & Energy

We offer a competitive, people-first benefits package designed to support every aspect of your life:

Benefits

• Comprehensive Benefits Coverage – 100% company-paid health, life, and disability insurance effective from Day 1 of employment
• Retirement Savings Program – Registered Retirement Savings Plan (RRSP) with the option of employer contribution
• Virtual Health Care – Company-paid program for employees and their dependents
• Employee & Family Assistance Program (EFAP) – Confidential support services
• Wellness Support – Fitness reimbursement to support wellbeing

Use of Artificial Intelligence in Talent Acquisition
At Capco, we use artificial intelligence (AI) tools to support and enhance several parts of talent acquisition. This includes using AI-enabled features within LinkedIn to help source potential candidates, speeding up routine recruitment communications such as emails and creating compelling and brand-aligned job postings that accurately reflect role requirements, and AI-scheduling applications to improve the efficiency of interview coordination.
AI is used as a support tool only. All hiring decisions are made by talent acquisition and hiring teams.

Why This Role Is Open
We are currently hiring for this role due to an existing or newly created vacancy within our organization. This position is open as part of our ongoing business needs, and we are actively reviewing applications to fill this role with a qualified candidate who can make an immediate impact.

Inclusion at Capco
We’re committed to making our recruitment process accessible and straightforward for everyone. If you need any adjustments at any stage, just let us know – we’ll be happy to help. We value each person’s unique perspective and contribution. At Capco, we believe that being yourself is your greatest strength. Our #BeYourselfAtWork culture encourages individuality and collaboration – a mindset that shapes how we work with clients and each other every day.

At Capco, we use artificial intelligence (AI) tools to support and enhance several parts of talent acquisition. This includes using AI-enabled features within LinkedIn to help source potential candidates, speeding up routine recruitment communications such as emails and creating compelling and brand-aligned job postings that accurately reflect role requirements, and AI-scheduling applications to improve the efficiency of interview coordination.
AI is used as a support tool only. All hiring decisions are made by talent acquisition and hiring teams.

#LI-Hybrid

About Behavox

Behavox is a cloud-native AI company providing an integrated controls platform for global banks, asset managers, hedge funds, private equity firms, insurance businesses, and commodity firms. The platform unifies communications and trade surveillance, compliant archiving, policy management as well as front-office analytics on a single, AI-native technology stack, delivered as a globally scalable SaaS-based cloud service.

At Behavox, our engineering culture is built around speed, experimentation, and technical excellence, following agile principles and rapid iteration. We constantly test and adopt the latest cloud technologies and AI tooling, optimising for fast feedback loops and execution. We look for people who can move fast, challenge conventional wisdom, and who want to work at the frontier of modern AI, SaaS platforms, and distributed systems.

Behavox is a high-performance organisation with a strong bias toward delivery, ownership, and responsibility. We commit, and we execute. We are building systems that are complex, mission-critical, and global in scale; systems that many consider too large or too difficult. To do that, we seek the smartest, most technically capable engineers and technologists who take end-to-end responsibility and want to win by building what others cannot.

Founded in 2014 and backed by SoftBank Vision Fund, Behavox is headquartered in London, with offices worldwide, including New York City, Montreal, Seattle, Singapore, and Tokyo.

About the Role

The Software Engineer (Java) operates at a senior engineer level, driving technical direction across core product domains. The role combines deep hands-on Java engineering with architectural ownership — from high-level system design and technology selection to leading delivery of critical, cross-cutting platform capabilities.

At this level, engineering excellence extends beyond implementation: the engineer determines the right approach to complex problems, communicates technical decisions across functions, participates in hiring, and is accountable for the long-term health of the systems they own. This level demands sound judgment on technology and business trade-offs and the ability to act as a technical lead. A defining expectation is mastery of AI-assisted engineering — leveraging agentic AI tools as force multipliers while retaining full ownership of architecture, quality, and technical outcomes.

What You'll Bring

• Expert Java engineering: Deep understanding of Java internals — GC tuning, Collections Framework, advanced concurrency (java.util.concurrent, multithreading), NIO/NIO2, performance profiling, and heap-dump analysis. Mastery of Spring Framework (IoC/DI, bean lifecycle, Spring Boot). SOLID principles, Clean Code practices, and GoF design patterns
• Software architecture and design patterns: Expertise in monolith and microservices architectural styles — including migration patterns and domain-driven decomposition. Inter-process communication design (REST, gRPC, messaging), transaction management in distributed systems (Sagas, 2PC), CQRS, Event Sourcing, and external API design focused on scalability, security, and documentation
• Cloud-native platforms and infrastructure: Experience designing high-availability and high-load systems on GCP (preferred), AWS, and Azure. Cloud security best practices: IAM, VPC, data encryption, JWT/JWS/JWE. Infrastructure as Code (Terraform or equivalent) and Twelve-Factor App methodology
• Observability, reliability and deployment: Implementing full observability stacks: structured logging, distributed tracing, metrics, and alerting. SLI/SLO/SLA frameworks. Deployment strategies: Rolling Updates, Blue/Green Deployments, Canary Releases
• AI-assisted engineering: Practitioner-level command of agentic AI tools applied to software engineering — encompassing prompt engineering techniques, AI context management and its limitations, sub-agents, skills and plugins, multi-agent orchestration, and team-of-agents architectures. Experience with Claude Code (Anthropic), Codex (OpenAI), or equivalent is mandatory

What You'll Do

• Architecture and technology leadership: Lead high-level design for complex, cross-service features. Evaluate and select appropriate technologies, frameworks, and architectural patterns before delegating implementation. Produce and maintain architecture documentation: design docs, ADRs, tech specs, and wiki pages
• Advanced Java feature implementation: Own and implement critical product components — including prototyping, architecture validation, and production-grade code. Ensure correctness, performance, and long-term maintainability with comprehensive test coverage (unit, integration, contract, component)
• Technical roadmap contribution: Drive the engineering agenda for assigned product areas. Proactively identify gaps in requirements, architectural limitations, and technical risks. Contribute to product roadmap planning and delivery estimation. Participate in hiring processes
• Cross-functional technical communication: Drive technical communication across engineering, product, DevOps, and ML teams. Communicate technical decisions clearly to non-technical stakeholders. Produce design documents and participate in tech talks and knowledge-sharing sessions
• AI-augmented engineering: Direct agentic AI tools (Claude Code, Codex, or equivalent) across the full engineering workflow — code generation, testing, refactoring, debugging, and documentation. Demonstrated ability to apply advanced prompt engineering, manage AI context limitations, compose multi-agent orchestration workflows, and critically evaluate AI-generated outputs for correctness, security, and quality. Ability to establish guardrails and improve agent configurations to raise the quality bar. AI proficiency amplifies — it does not replace — deep engineering judgment and technical accountability

What We Offer

• The opportunity to work on a global, mission-critical AI platform alongside the best engineers and technologists across multiple geographies
• A role with real ownership and impact, building complex systems at scale in an environment that values speed, experimentation, and technical excellence
• A highly attractive benefits package, including competitive cash compensation, an equity award aligned with long-term value creation, and comprehensive health insurance for employees and their families
• Modern, comfortable offices in Montreal/ Toronto downtown, with an expectation of working from the office 1 day per week, reflecting our belief in strong in-person collaboration, while remaining flexible to accommodate remote work for candidates who live in other Canadian cities
• A generous time-off policy of 30 days annually, plus public holidays and sick leave, recognising the importance of sustained high performance

About Our Process

Our selection process is designed to rigorously assess a candidate’s depth of technical knowledge, problem-solving ability, and alignment with Behavox’s mission and core values.

As part of the process, candidates will first participate in a series of interviews focused on evaluating their technical expertise and engineering judgment. Candidates who successfully progress through these interviews will then be invited to complete a live technical exercise. The purpose of this live technical assessment is to validate the candidate’s stated technical competencies and assess their ability to solve complex problems with speed, accuracy, and sound engineering judgment. Note that whenever possible, we aim to conduct interviews in person at our offices.

We recognise and respect the time candidates invest in this process. In return, Behavox commits significant time and resources to ensure that those who join us have the capability, judgment, and alignment required to operate at the speed and level of complexity our work demands. We value efficiency and clarity on both sides; if at any point we determine that a candidate is not a fit, we reserve the right to immediately conclude the interview or the technical assessment.

Please note the following:

• A core objective of the process is to objectively assess individual knowledge and competencies. The use of AI tools or external assistance during live interviews or technical exercises is strictly prohibited (unless explicitly instructed otherwise) and will result in immediate disqualification.
• Interviews and technical sessions may be recorded for internal review to support fairness, consistency, and collaborative decision-making within the hiring team.

MaintainX is the world's leading AI-powered maintenance and asset management platform, serving 13,000+ customers including Duracell, Shell, Cintas, and Brenntag. We raised $150M in Series D funding led by Bessemer Venture Partners and Bain Capital Ventures, bringing our total funding to $254M. We were named to the Forbes 2025 Cloud 100, the definitive ranking of the top 100 private cloud companies in the world. We're growing fast and hiring the engineering talent to match.

We're looking for a Senior Software Engineer to own the constraint-solving engine behind our Scheduling Agent, one of the most strategic bets on our Planning & Scheduling roadmap. The engine is a Python service built on CP-SAT that takes work orders, technicians, and a mix of hard and soft constraints, and produces a feasible weekly schedule that enterprise maintenance teams can trust. Your focus will be evolving the solver to handle increasingly complex, real-world scheduling scenarios and exposing it as tools for GenAI agent workflows.

This is a high-ownership role. You'll have the space to shape the modeling approach, partner closely with product and design on what scheduler users actually need, and ship iteratively against feedback from real enterprise customers.

What you'll do

• Own and evolve the Python optimization service that powers the Scheduling Agent, modeling, solving, and iterating on the constraint formulation as new use cases emerge.
• Design and implement increasingly sophisticated scheduling capabilities: trade and crew constraints, irregular capacity patterns, production downtime windows, multi-site considerations, and reactive re-scheduling.
• Build and maintain API routes and tools that expose the solver to GenAI agent workflows (tool calling, structured input/output).
• Partner with PM and design to translate messy real-world scheduling problems into solver constraints, and push back when "optimal" isn't what users actually want.
• Iterate the solver with real users via design partnerships and pilot deployments. Take feedback from human schedulers seriously and reflect it back into the model.
• Contribute to the surrounding Python service: performance, observability, testing, and reliability of the optimization runtime.
• Help shape how scheduling intelligence integrates with the broader MaintainX product over time, including learning from execution data to improve solver inputs.

About you

• 5+ years of professional software engineering experience, with significant time spent on optimization, constraint programming, or operations research problems shipped to real users.
• Strong fluency with CP-SAT and at least one other optimization paradigm (MILP via Gurobi/CPLEX/HiGHS, metaheuristics, or similar). You've hit the limits of one approach and made informed choices about when to use which.
• Solid Python service engineering: APIs, async, testing, profiling, observability. You can own a production service end-to-end.
• Academic grounding in Operations Research, Industrial Engineering, Computer Science, or a related quantitative field, at minimum a strong undergraduate foundation; advanced degrees are common in this space but not required.
• Track record of iterating optimization systems with real users, you've felt what happens when a human rejects the "optimal" answer and you've redesigned the model in response.
• Product mindset and delivery orientation, you ship, you measure, you iterate. You think about the user outcome, not just the objective function.
• Comfort with ambiguity. You can co-design the constraint data model with the team rather than waiting for a clean spec.
• Familiarity with GenAI tooling (LLM tool calling, structured output, prompt design for constrained generation) is expected.

Nice to have

• Experience at a known, reputable product company shipping optimization or scheduling products at scale.
• Exposure to learning-augmented optimization, using historical execution data to estimate durations, priors, or constraint weights.
• Domain experience in scheduling, workforce management, field service, manufacturing, logistics, or similar resource-constrained planning problems.
• Tech-lead experience or interest in growing into a tech-lead role on this team.

What's in it for you

• Competitive salary and meaningful equity opportunities.
• Healthcare, dental, and vision coverage.
• 401(k) / RRSP enrollment program.
• Take what you need PTO.
• A Work Culture where:
• You'll work alongside folks across the globe that reflect the MaintainX values: Smart Humble Optimists.
• We believe in meritocracy, where ideas and effort are publicly celebrated.

About us

Our mission is to deliver one platform for maintenance, repair & operations teams to keep the physical world running. We believe the greatest asset in any organization is the people. That's why we built an intuitive, mobile-first solution to help boost productivity and collaboration across teams and locations.

MaintainX is committed to creating a diverse environment. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.

#LI-Remote

We're looking for a Senior SDET who thinks deeply about quality in systems that are inherently non-deterministic. Agentic AI doesn't fail the same way traditional software does — and testing it requires a new toolkit: eval frameworks, prompt regression, tool-call reliability, adversarial scenarios, and more.

You'll own the entire quality infrastructure across our product portfolio — from test data and CI pipelines to the standards and culture of how we ship. You'll work directly with product, devops, and AI engineering, with no layers between your decisions and their impact.

What You'll Own

• Test infrastructure, test data, test processes across the entire product portfolio while working with Devops and Infrastructure engineers
• Test Framework - build and enhance automated testing frameworks and tools that facilitate automated testing across different layers of application.
• The reliability bar for all Web applications, Mobile applications and AI agent outputs — from hallucination detection to latency regressions and tool-call correctness
• Test infrastructure, test data, and test processes across the entire product portfolio, alongside DevOps and Infrastructure engineers
• Automated testing frameworks that span all layers of the application — unit, integration, contract, and end-to-end
• Evaluation frameworks designed for LLM-based systems: non-deterministic output scoring, prompt regression, and adversarial test suites
• HIPAA-aware test data management — de-identification pipelines, synthetic data generation, and audit trail validation
• Integration of automated tests into CI/CD pipelines for continuous delivery confidence
• Build stability monitoring and release gate enforcement before any deployment
• Documentation of test plans, test results, and evaluation standards to support knowledge sharing
• The "safety net" for product quality — you define what done looks like

What We're Looking For

• 8+ years of hands-on SDET experience, with recent work building or testing agentic AI systems (single- or multi-agent) in production
• Experience in healthcare or life sciences — you understand what's at stake when a system fails in this domain
• A true tester's mindset: you seek out edge cases, adversarial inputs, and failure modes others overlook
• Proficiency across the full test pyramid — unit, integration, system, performance, and exploratory — plus familiarity with LLM-specific evaluation approaches
• Strong debugging skills across multi-tier web and mobile architectures; comfortable jumping into production incidents
• Proficiency with testing frameworks such as Jest, React Testing Library, Supertest, and pytest.
• Hands-on experience with testing tools like Cypress, Playwright, Supertest, and pytest (including requests or Selenium-based testing)
• Experience testing RESTful APIs using tools like Postman or Supertest
• Solid command of JavaScript and Python

Bonus Points

• Multi-cloud experience (AWS, Azure, GCP)
• Experience with red-teaming or adversarial testing of AI systems
• Native mobile testing experience (iOS, Android)
• Prior work with 21 CFR Part 11, GxP, or similar regulated-software validation frameworks

Why Medeloop

• Ownership from day one: small team, high-trust, no layers between your work and its impact
• Technically ambitious: you'll build AI-powered workflows, not just support them
• Real-world stakes: your work accelerates drug development, addresses health equity, and improves clinical research for institutions that matter

Strong foundation: Series A, top-tier investors, and a data asset (200M+ patient records) that most companies spend years trying to build

About the Role

As a Context Engineer at CapIntel, you'll sit at the intersection of AI infrastructure and engineering. You will be responsible for how large language models are integrated into our core platform and how our engineering team adopts agentic workflows. This is a hands-on, production-focused role, not a research one. You'll build the systems that make our AI features reliable, accurate, and scalable for the wealth management enterprises that depend on us.

You'll be embedded in development teams working closely with engineers, product managers, and domain experts across the organization to design and deliver LLM-powered capabilities that directly enhance the advisor and client experience. As one of the first practitioners in this discipline at CapIntel, you'll also help define what context engineering looks like here: setting patterns and practices the broader team can build on.

This role is ideal for someone who thinks in systems, cares about production reliability over demo-day performance, and is energized by working in a discipline that is evolving quickly.

What You'll Do

• Design and implement LLM-powered features into our core application via model APIs (e.g. Anthropic, OpenAI, Cohere), with a focus on reliability and production-readiness
• Architect and maintain retrieval-augmented generation (RAG) pipelines, connecting language models to internal knowledge bases, databases, and live data sources
• Manage context window strategy, determining what information enters the model, when, in what format, and at what level of compression to optimise for accuracy, cost, and latency
• Design and implement agentic workflows enabling the platform to handle multi-step, autonomous tasks
• Build guardrail and output validation layers that constrain model behaviour and ensure AI features act within well-defined, compliant boundaries
• Develop reusable agent primitives, prompt templates, and workflow components that other engineers can build on independently
• Build evaluation frameworks to measure context effectiveness, output quality, and agent reliability in production
• Monitor deployed AI systems for failure patterns and implement mitigation strategies, feeding learnings back into continuous improvement cycles
• Collaborate with Product, Product Engineering, Implementation, and Data teams to translate business requirements, and proof of concepts into production AI system specifications
• Act as an internal practitioner and resource helping upskill the broader engineering team on context engineering principles and agentic best practices

What We're Looking For

• 5+ years of professional software engineering experience, with at least 1–2 years working with LLMs in a production context
• Strong experience with Python or Node and building API-integrated backend services
• Hands-on experience with an orchestration or execution framework
• Working knowledge of RAG architecture, vector databases (e.g. Pinecone, pgVector, AWS OpenSearch), and semantic search
• Familiarity with context management techniques: summarisation, chunking, session splitting, and memory strategies
• Experience building or consuming REST APIs and integrating with third-party services
• Comfortable collaborating with cross-functional teams in a fast-paced, high-growth environment
• Strong problem-solving instincts and a willingness to learn and adapt as the field evolves

Nice to Have

• Experience with the Model Context Protocol (MCP) or similar tool-integration standards
• Familiarity with LLMOps practices: tracing, observability (e.g. LangSmith, Datadog), and model versioning
• Exposure to multi-agent architectures and orchestration patterns
• Knowledge of AI output validation, context safety, and governance considerations particularly relevant in regulated industries like financial services
• Familiarity with AWS or cloud-based infrastructure and containerised deployments (Docker, Kubernetes)
• Ability to communicate technical concepts clearly to both technical and non-technical partners