RolepaperAbout this role
<p>At JetBrains, we build developer tools used by millions of engineers. The AI for Code team works on the next generation of coding agents and agentic workflows: systems that can understand codebases, plan and execute multi-step tasks, collaborate with developers, and ship reliable results inside real development environments.</p> <p>We are looking for a Staff/Senior AI Engineer to join the team and support these efforts. This role is for someone who can take our internal coding models, such as Mellum2, as well as open-weight models, and turn them into production-ready coding agents for our users. You’ll work on model training and fine-tuning, context engineering, tool use, evaluation, feedback loops, and product integration. This is not research in isolation – you’ll build systems that are used by tens of thousands of developers.</p> <h2>What you’ll do:</h2> <ul> <li>Build production-ready coding agents and agentic workflows for real developer tasks inside JetBrains products.</li> <li>Turn promising model capabilities into dependable product behavior through prompt design, context construction, fine-tuning, instruction-tuning, or other post-training techniques where appropriate.</li> <li>Design and improve the agent loop itself, including tool use, execution strategy, safeguards, and task completion quality.</li> <li>Create evaluation suites and quality infrastructure for agent behavior, including online and offline evaluations, regression checks, failure analysis, and release criteria.</li> <li>Build feedback loops from real usage, using logs, user signals, and edge cases to improve data, evaluations, and agent behavior.</li> <li>Work with both hosted frontier APIs and self-hosted or open-weight models, making pragmatic decisions about where each model belongs based on capability, latency, reliability, privacy, and cost.</li> <li>Collaborate closely with product managers, software engineers, ML engineers, and researchers to ship features end to end.</li> <li>Help define the technical direction for future work, especially in ambiguous areas where we need strong judgment rather than a prewritten playbook.</li> </ul> <h2>What we’re looking for:</h2> <ul> <li>Strong software engineering fundamentals and a track record of shipping complex systems to production.</li> <li>Hands-on experience building LLM-powered products, coding agents, or other AI systems.</li> <li>Experience improving model behavior through systematic iteration, whether via prompting, context engineering, fine-tuning, preference optimization, or broader post-training methods.</li> <li>Practical experience with evaluation and benchmarking for LLM systems, including defining task-grounded success metrics and catching regressions.</li> <li>Experience working from noisy real-world signals rather than only from clean benchmark datasets.</li> <li>Good judgment about trade-offs between model quality, latency, reliability, privacy, and cost.</li> <li>Confidence working with ambiguity and taking ownership of a direction over multiple iterations.</li> <li>Strong communication skills and the ability to align engineering and product decisions.</li> </ul> <h2>What success looks like in the first year:</h2> <ul> <li>You ship one or more agent capabilities that users can rely on for meaningful work, not just demos.</li> <li>You establish better evaluation coverage and clearer release criteria for agent behavior.</li> <li>You help the team build a repeatable loop from idea to shipped capability: prototype, evaluate, learn from usage, improve, and scale.</li> </ul> <h2>Why join us?</h2> <p>You’ll help define what practical, trustworthy AI for