Why Kimchi?

Kimchi is the AI platform inside CAST AI. We started by helping companies run LLMs on their own Kubernetes clusters - now we're building the execution layer where agents do real work.

Our Infrastructure today: multi-model inference (MiniMax, Kimi, GLM-5, Nemotron, DeepSeek) with intelligent routing, an OpenAI-compatible API, and deployment flexibility from our GPUs to your VPC. The inference layer is the foundation. What we're hiring for sits on top of it: coding agents, agent runtimes, orchestration systems, and the reliability engineering that makes them actually finish things.

Tech Stack: TypeScript, Go, Kubernetes, AWS/GCP/Azure, MCP, Prometheus/Grafana/Loki, GitLab CI, ArgoCD.

Why harness engineering matters here
OpenAI and Anthropic ship models. They also ship one harness each - the scaffolding that turns a raw model into something that can plan, execute, recover, and complete work. We ship a different kind of harness: one built for cost-conscious, long-horizon autonomy, running on inference infrastructure we control end-to-end.
A decent model with a great harness beats a great model with a bad harness. We've watched this play out. The gap between what today's models can do and what you see them doing is largely a harness gap - and that gap is where we operate.

What you'll build
The ratchet.
Every time our agent makes a mistake, we engineer a solution so it never makes that mistake again. That means hooks that enforce constraints the model "knows" but forgets: pre-commit lint checks, permission gates, context compaction before the window fills. Success is silent, failures are verbose.

Long-horizon execution.
Our harness is built around spec-driven autonomy: meta-prompting, fresh context per task, worktree-per-slice git strategy, automatic replanning, crash recovery, stuck detection. We're implementing Ralph loops - when the model tries to exit, we intercept and reinject the goal into a fresh context. The agent reads state from disk and continues. Multi-session, multi-day work, without context rot.

Planner/executor splits.
Planning with a reasoning model, executing with a fast one, evaluating with a third. Separating generation from evaluation beats self-verification because agents reliably skew positive when grading their own work.

The harness surface.
CLI, TUI, MCP integration, sandboxed execution, telemetry. Our AGENTS.md is short - every line traces to a specific thing that went wrong. TypeScript on the surface, Go where it matters.

Memory and context.
Moving agents off laptops, giving them state that survives across sessions, managing context so information lands where it's actionable. Compaction, tool-call offloading, progressive skill disclosure.

What makes this different (with receipts)
You've seen the pitch: "we route to the best model." Everyone says that. Here's what we actually have:

• GPU infrastructure we own. Not just an API reseller. From GPU placement across clouds to the inference endpoint your agent calls - we control the cost curve.
• A harness-first thesis. We treat agent failures as configuration problems, not model problems. When we moved from a stock harness to our own, completion rates on internal benchmarks improved by 40%+ on the same model.
• Agents.md that earns every line. No brainstormed rules - every constraint in our system prompt traces to a real failure we saw and fixed.

Requirements:

• You've used AI coding agents in anger. Not demos - real work. You have opinions about Claude Code, Codex, OpenCode, Cursor. You know what it feels like when an agent gets stuck and why.
• Strong TypeScript or Go in production. Comfort moving between them. Our surface is TypeScript; our core is Go.
• You think in harness terms. You read "the agent hallucinated" and your first instinct is to ask what context it was missing, what hook should have caught it, what constraint should exist.
• You drive features end-to-end. Design → build → ship → measure → iterate. We don't have layers that absorb ambiguity for you.

Responsibilities:

• Build and evolve the agent harness - ship hooks, permission gates, and context compaction. Every AGENTS.md constraint traces to a failure you personally diagnosed.
• Own long-horizon execution - multi-session task completion via spec-driven prompting, worktree-per-slice git, Ralph loop recovery, and stuck detection. Completion rate is your metric.
• Architect planner/executor/evaluator pipelines - planning with a reasoning model, execution with a fast one, evaluation with a third. No self-verification.
• Manage agent memory and context - state persistence across sessions, context compaction, tool-call offloading. Zero context rot on multi-day work.
• Own the harness surface - CLI, TUI, MCP integrations, sandboxed execution, telemetry. TypeScript on the surface, Go where it matters.

What success looks like (after 6 months):

• You've shipped at least one major harness feature end-to-end: designed it, built it, measured it, iterated.
• You've added constraints to our AGENTS.md based on failures you personally observed and diagnosed.
• You've improved a measurable reliability metric - completion rate, context efficiency, or cost per successful task.
• You've formed strong opinions about where our harness is load-bearing and where it's dead weight.

What’s in it for you?

• Competitive salary (€6,500 - €9,000 gross, depending on the level of experience).
• Enjoy a flexible, remote-first global environment.
• Collaborate with a global team of cloud experts and innovators, passionate about pushing the boundaries of Kubernetes technology
• Equity options.
• Get quick feedback with a fast-paced workflow. Most feature projects are completed in 1 to 4 weeks.
• Spend 10% of your work time on personal projects or self-improvement. 
• Learning budget for professional and personal development - including access to international conferences and courses that elevate your skills.
• Annual hackathon to spark new ideas and strengthen team bonds.
• Team-building budget and company events to connect with your colleagues.
• Equipment budget to ensure you have everything you need.
• Extra days off to help maintain a healthy work-life balance.

This is a location-specific opportunity. We are currently accepting applications from candidates residing in the following European countries: Bulgaria, Croatia, Estonia, Greece, Hungary, Latvia, Lithuania, Poland, Romania, Slovakia, Slovenia, and Ukraine.

*As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr.
*Please note that Cast AI does not provide any form of visa sponsorship/work permit.

#LI-Remote

How You'll Make an Impact: 

As a Senior DevOps Engineer at Cloudbeds, your goal is to constantly improve and scale our SaaS platform to deliver an exceptional experience to hoteliers and their guests worldwide. You'll own the creation, monitoring, automation, and support of our cloud infrastructure and delivery pipelines — enabling product teams to ship high-quality software with speed and confidence. Working within a bottom-up culture that values healthy debate and collaborative problem-solving, you'll have real influence over architecture decisions and the opportunity to shape how we scale infrastructure for one of the fastest-growing hospitality technology platforms in the world.

Our Infrastructure Team: 

Our Infrastructure team is made up of engineers who take genuine pride in their craft, owning projects end-to-end and holding themselves to a high bar. We're passionate about technology and constantly pushing to improve our stack, not just maintain it. If you thrive in an environment where attention to detail matters, great communication is a given, and you're comfortable challenging the status quo to make things better, you'll feel right at home here.

What You Bring to the Team:

• Architect, improve, and scale Cloudbeds' cloud infrastructure on AWS, with a focus on reliability, security, and performance
• Build and evolve our Kubernetes (EKS) platform, driving adoption of containerization best practices across engineering teams
• Automate infrastructure provisioning and configuration using infrastructure-as-code tools like Terraform
• Design, build, and maintain CI/CD pipelines (GitHub Actions, ArgoCD) that enable fast, reliable software delivery
• Partner with product and engineering teams to drive projects to production, sharing DevOps expertise and ensuring strong environment configuration from the infrastructure side
• Maintain and improve monitoring, logging, and alerting systems to ensure platform health and rapid incident response
• Participate in on-call rotation to support production environment stability.

What Sets You Up for Success:

• 5+ years of experience as a DevOps Engineer working hands-on with AWS (networking, compute, storage, databases, queues, cache, permissions).
• 5+ years of strong Kubernetes and Docker experience, including implementing and scaling EKS platforms at production scale.
• Deep expertise with Terraform for infrastructure-as-code and configuration management.
• Proven experience building and supporting CI/CD pipelines using GitHub Actions and ArgoCD.
• Strong knowledge of monitoring and observability tools such as Datadog, Prometheus, Loki, or AWS CloudWatch.
• Working knowledge of web application servers (NGINX, Ingress controllers), databases (MySQL, PostgreSQL, Aurora), caching (Redis, Memcached), and queue technologies (SQS).
• Ability to write Bash and/or Python scripts to automate operational tasks.
• Strong Linux system administration skills and solid networking fundamentals.
• Excellent written and verbal English communication skills; comfortable working asynchronously across a globally distributed remote team.

#LI-REMOTE #LI-IK1

What We Do: AI Service Management (AISM):

Aisera offers the world's first AI-driven service experience solution that automates operations and support for IT, Sales and customer service, making businesses and customers successful by offering consumer-like self-service resolutions to users. Aisera fast tracks the digital transformation journey with user and service behavioral intelligence that drives end-to-end automation of tasks, actions, and business processes. Aisera is a top-tier, VC-funded startup headquartered in Palo Alto, Calif. and a strategic partner with AWS, Microsoft Azure, Google Cloud, ServiceNow and Salesforce.

Aisera has received numerous recognitions, including the following: Forbes AI50; CNBC Upstart 100 Top Startup; Gartner Cool Vendor; Red Herring Top 100 Global Innovator; CIO Innovation Startup Award; CIO Review Top ITSM Solution; Aragon Research Hot Vendor; TiE50 Startup Award; and Silicon Review 50 Most Admired Companies.

The Role: 

Lead AI/ML research and development initiatives while growing as a software engineer. Drive machine learning innovation with strong research acumen while building production-ready ML systems. Partner with AI Systems Tech Lead for technical mentorship and system integration.

Key Responsibilities:

• Lead ML research, experimentation, and development from concept to deployment
• Design and implement novel ML/AI approaches, staying current with cutting-edge research and methodologies
• Architect ML pipelines, training infrastructure, and model evaluation frameworks
• Guide ML engineering decisions including model selection, feature engineering, and optimization strategies
• Translate academic insights into practical applications
• Mentor junior ML engineers and establish ML best practices across the team
• Work closely with AI Systems Tech Leads to ensure delivery of optimized AI systems and services to production
• Enforce data governance and privacy: Follow processes and implement methods that ensure data governance, privacy, and security. 
• Collaborate with cross-functional teams: Work closely with product managers, and other stakeholders to ensure the AI/ML solutions align with the organization's goals and objectives.
• Communicate effectively: Clearly document your work and effectively communicate your findings, insights, and recommendations to both technical and non-technical stakeholders, fostering a collaborative and informed environment.

Required Expertise:

• 5+ years in ML engineering with demonstrated advanced development or research capabilities (innovative projects, publications, theses)
• Advanced degree in AI/ML or related subjects with relevant undergraduate degree
• Deep understanding of ML fundamentals: deep learning, statistical modeling, optimization, and evaluation methodologies
• Strong Python skills with ML libraries (PyTorch, TensorFlow, scikit-learn, Hugging Face)
• Experience with ML experiment tracking, model versioning, and reproducible research practices
• Ability to translate research papers into working implementations
• At least a year of leadership experience driving technical ML initiatives for a small team
• Solid foundation in software development practices (testing, version control, code review)

Growth Opportunities:

• Opportunity to lead both research direction and technical implementation
• Direct involvement in productionizing cutting-edge ML research
• Accelerated software engineering development 

Preferred (in order):

• Background in NLP 
• Experience with distributed training, MLOps, and cloud ML platforms
• Track record of research publications or open-source ML contributions
• Enterprise SaaS experience 

This role is in a Product-building AI/ML team. This is a Greece-based, full-time, employee-status, fully remote position. 

Aisera is Global and our success draws upon the diverse viewpoints, skills and experiences of our employees. We are proud to be an equal opportunity employer and are committed to equal employment opportunities regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, marital status, disability, gender identity or veteran status.

Aisera is a leading provider of AI Copilot solutions, utilizing AiseraGPT and Generative AI to facilitate business transformation and drive revenue growth through a self-service model. Aisera’s AI Copilot uses industry and domain-specific LLMs to deliver human-like experiencs and auto- remediate requests through AI workflows. With 400+ integrations and 1200+ prebuilt workflows, customers achieve 75%+ automation and 90% cost reduction. Aisera has received numerous recognitions, including Leader in the 2024 Gartner Magic Quadrant™ for Artificial Intelligence Applications in ITSM, FastCompany Best Workplaces for Innovators, Inc 5000 Award for Fastest Growth, Forbes AI50, EY Entrepreneur of the Year 2023, CNBC Upstart 100 Top Startup, Gartner Cool Vendor, Red Herring Top 100 Global Innovator, CIO Innovation Startup Award, CIO Review Top ITSM Solution, and Silicon Review 50 Most Admired Companies.

The Role
Take this opportunity to lead the design and development of advanced AI systems including intelligent agents, conversational interfaces, and retrieval-augmented generation (RAG) architectures and systems. Drive technical strategy and implementation for next-generation AI products.

Responsibilities

• Architect and build scalable agentic AI systems capable of autonomous decision-making and task execution
• Architect, design and optimize dialog agents with natural language understanding, context management, and multi-turn conversation capabilities
• Develop and optimize robust search and retrieval systems for RAG implementations, including vector databases, embedding strategies, and knowledge integration
• Take ownership of complex system design, from proof-of-concept to production deployment
• Establish best practices for AI model integration, prompt engineering, and system reliability
• Collaborate with product teams to translate business requirements into technical AI solutions
• Develop and maintain scalable, efficient data pipelines that automate the ingestion, transformation, and storage of data
• Identify performance bottlenecks and improve systems scalability.

Requirements

• At least 7 years in senior software engineering roles, with 2+ years as tech lead or architect 
• 2+ recent years professional work on AI or Search systems 
• Expertise in vector search, embedding models, or RAG system optimization
• Strong background in distributed systems, APIs, and cloud-native AI infrastructure
• Experience with AI frameworks (LangChain, LlamaIndex, etc.), and vector databases or information retrieval systems (preferably Elastic)
• Solid understanding of software development principles and architectural best practices.
• Professional experience with messaging systems such as Kafka, RabbitMQ, or similar technologies.
• Professional experience with cloud platforms such as AWS, GCP or Azure.
• Proficiency in using Docker, Kubernetes, or similar containerization and orchestration tools.
• Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.

Preferred Qualifications (in order):

• Ph.D. in distributed systems, AI systems, or related area
• Familiarity with machine learning concepts and libraries (e.g., Pandas, NumPy, PyTorch).
• Experience with LLM integration, prompt engineering, and AI orchestration frameworks. 

This is a Greece-based, full-time, employee-status, fully remote position.  

Aisera is Global and our success draws upon the diverse viewpoints, skills and experiences of our employees. We are proud to be an equal opportunity employer and are committed to equal employment opportunities regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, marital status, disability, gender identity or veteran status.