Software engineers and AI agents alike suffer from the same problem: finding that one person or place that will answer their tough, specific question. Many solutions promise to solve this with similarity search in vector databases. Unfortunately, finding the answer is often a puzzle with pieces to be collected across a myriad of contradictory sources and cannot be solved without surgical search and careful reasoning. 

Spectrum collects data from an organization’s code, docs, and issues, and organizes knowledge in a unified ontology that AI agents can efficiently search through and reason over. We aim to revolutionize the semantic layer space for software-building organizations and move beyond specs that fall out of sync with code, introducing a living spec – one that’s extracted from the whole system and used to keep it aligned. Spectrum is meant to be the single source of truth for all product and architectural knowledge.

Spectrum is a resident of JetBrains' startup incubator, with startup speed and autonomy, and backed by 25 years of developer tooling expertise. We are looking for a top-class ML Engineer who will help us shape the future of software development. You will own our AI and ML engineering stack and help define the research agenda for our team. Your technical vision and design decisions will directly shape the product and determine its success.

Your responsibilities will include:

• Designing and building the ML/LLM solution for data ingestion, knowledge extraction, retrieval, and subsequent reasoning.
• Creating the datasets, metrics, and pipelines that drive measurable improvements across the system.
• Architecting and improving agents for context retrieval, knowledge extraction, and data alignment, which includes prompt engineering, model selection, and inference optimization.
• Establishing MLOps practices, including orchestration, observability, and experiment tracking.
• Collaborating with the engineering team on system design and with JetBrains Research on the research agenda.
• Defining hiring criteria, growing the ML team, and shaping the ML team culture.

We expect you to have:

• A proven track record as an ML/AI Lead.
• At least five years of experience in ML/AI systems, with at least two years focused on LLMs and generative AI.
• A deep understanding of the LLM ecosystem, including model architectures and fine-tuning approaches.
• Hands-on experience with:
• Prompt engineering and LLM pipeline design, including evaluation.
• Agentic frameworks such as LangChain, LlamaIndex, LangSmith, smolagents, or an equivalent.
• Vector databases and retrieval-augmented generation (RAG) patterns.
• Deploying and scaling LLM-powered applications using APIs (e.g. OpenAI or Anthropic) or open-source models.
• Strong Python skills – Kotlin knowledge would be a plus.
• Excellent communication skills, with the ability to explain complex technical concepts to diverse audiences.
• Proficiency in English, both written and verbal. 

Our ideal candidate would have:

• Experience with ontologies, knowledge graphs, or graph-based reasoning.
• Experience in early-stage startups – you enjoy the zero-to-one phase.
• The ability to think strategically about product-led AI, beyond just training models in isolation.
• A background in code analysis, developer tools, or software engineering research.
• Experience with multi-agent systems or complex agentic workflows.
• Actively contributed to relevant open-source projects or publications.

What we offer

• A competitive salary and JetBrains benefits.
• A generous runway and corporate resources with startup autonomy.

#LI-KP1

About the Team

Miro is on a mission to empower teams to create the next big thing, and our teams are at the forefront of making that vision a reality. Our teams drive AI-powered innovation across Miro's platform by building robust technical foundations, delightful product features, and intelligent capabilities that transform how users interact with content on the canvas. Whether developing structured widget capabilities that help users visualize and interact with complex information, building AI platform infrastructure, or creating intelligent features that anticipate user needs, our work is foundational to Miro's evolution.

About the Role

As an AI Engineer, you'll design and build AI-driven capabilities that enhance how users create, transform, and collaborate on canvas. You'll bridge AI innovation and product delivery - shipping delightful, safe, and reliable experiences that leverage cutting-edge LLMs while maintaining the performance and polish users expect from Miro's collaborative canvas.

What you’ll do

• Design, develop, and ship AI-driven capabilities—including agents, intelligent assistants, context-aware prediction, and generative AI—using Python, top-tier LLMs, TypeScript, React, Canvas, and WebGL
• Engineer high-performing AI workflows leveraging LLMs (OpenAI, Anthropic Claude, Google Gemini), prompt engineering, and generative techniques—ensuring reliability, scalability, and maintainability
• Execute end-to-end AI projects from conceptualization and prototyping to production code, collaborating closely with product managers, designers, and engineers
• Experiment and iterate on AI capabilities within your team domain, staying ahead of emerging AI tools, frameworks, and techniques
• Champion best practices in AI system development—including evaluations, LLMOps, CI/CD, observability, and ethical AI principles
• Measure and optimize AI performance, establishing benchmarks for user engagement, model accuracy, latency, error rate, and drift
• Write clean, well-tested, maintainable code, participating in code reviews and® technical discussions across the stream
• Troubleshoot and resolve production issues, ensuring high availability and performance

What you’ll need

• 3+ years of professional experience with a proven track record delivering AI-first capabilities in customer-facing products—driving value through features users directly interact with
• Excellent communication skills, able to translate complex technical concepts for non-technical stakeholders
• Strong Python skills and familiarity with FE technologies (e.g. Typescript, React etc)
• Demonstrated expertise in prompt engineering and context engineering using top-tier LLMs (OpenAI GPT, Anthropic Claude, Google Gemini)
• Ability to develop high-quality, production-ready code within complex codebases
• Experience with LLM evaluation frameworks and a track record of building evals that meaningfully inform model selection, prompt iteration, or feature quality.
• Solid understanding of ML fundamentals, including probabilistic modeling, evaluation techniques, and deep neural networks
• Experience with LLMOps and cloud services (AWS, Azure, Amazon Bedrock, etc.)
• AI-First Proficiency. We’re building for an AI-first future, and we’re looking for graduates who aren’t just using AI—they’re mastering it. We’re excited to meet early-career engineers who have moved beyond simple chat prompts and have truly integrated AI into their development flow. Whether it’s using AI agents for autonomous debugging, analyzing logs, or rapidly prototyping and shipping features to production, we value the ability to "pilot" these tools to deliver high-quality code at an ambitious pace.
• Nice-to-have: Experience with rendering technologies like WebGL, Canvas API, or 2D graphics libraries (PixiJS, Skia)
• Nice-to-have: Real-time technologies experience (WebSocket)
• Nice-to-have: Vector databases, RAG pipelines, LangChain, or agent frameworks
• Nice-to-have: Multi-modal AI or long-context handling
• Nice-to-have: ML frameworks: PyTorch, TensorFlow, Hugging Face Transformers

What's in it for you

We want you to feel supported, connected, and ready to grow. Our global benefits package generally includes equity, a wellbeing benefit, a WFH equipment allowance, and an annual Learning & Development stipend. Join a diverse team where you can do your best work. Full benefits may differ per location. If you would like to learn more about location-specific benefits, please refer to our Global Miro benefits board.

Recruiter: #LI-JR1