Senior Research Engineer (Agentic Behavior)

About the role

<p>At JetBrains, code is our passion. Ever since we started, back in 2000, we've been striving to make the strongest, most effective developer tools on earth. Today, AI-powered coding agents are becoming a core part of how developers write Kotlin – and we want to make sure they write it well.</p> <p>The Kotlin AI Value Stream team is responsible for how AI agents understand, generate, and improve Kotlin code across all platforms: Android, Kotlin Multiplatform, server-side, web, desktop, and others. We build the evaluation infrastructure, error analysis tools, and post-training pipelines that measure and improve agent behavior on real Kotlin developer tasks.</p> <p>As a Research Engineer on this team, you'll own the end-to-end loop: Analyze how agents fail on Kotlin → build evals that capture those failures → research and implement methods to fix them → measure the improvement. Your work will directly shape how millions of developers experience Kotlin through AI coding agents.</p> <h2><strong>As part of our team, you will:</strong></h2> <p><strong>Build tools for agentic error analysis</strong></p> <ul> <li>Design and implement tooling to systematically capture, classify, and analyse errors that AI coding agents make when generating Kotlin code.</li> <li>Build observability pipelines over agentic traces – mining patterns from agent sessions in JetBrains IDEs, Junie, Claude Code, Cursor, and other coding agents.</li> </ul> <p><strong>Build evaluation pipelines</strong></p> <ul> <li>Design, implement, and maintain evaluation pipelines that measure Kotlin code generation quality across dimensions, including correctness, idiomaticity, build success, framework usage, and test coverage.</li> <li>Build simulation environments where coding agents can be measured on realistic Kotlin developer tasks – from greenfield KMP projects and Gradle dependency management to migrating Spring applications from Java to Kotlin.</li> <li>Own evaluation infrastructure: metrics, experiment tracking, automated regression checks, and reproducible benchmarking.</li> </ul> <p><strong>Research methods for improving agent and model behavior on Kotlin</strong></p> <ul> <li>Experiment with post-training techniques (SFT, DPO, GRPO) to improve how models handle Kotlin-specific patterns, idioms, and frameworks.</li> <li>Investigate context engineering approaches: CLAUDE.md/AGENTS.md files, compiler-as-verifier feedback loops, Kotlin LSP integration, and MCP-based tooling.</li> <li>Run experiments to measure impact: A/B comparisons, benchmark suites, and before/after analyses on real codebases.</li> <li>Collaborate with model providers (Anthropic, OpenAI, and Google) to translate Kotlin-specific findings into model improvements.</li> </ul> <p><strong>Build public Kotlin benchmarks</strong></p> <ul> <li>Design and build open-source benchmarks that measure AI coding agent performance on Kotlin tasks and eventually become the standard reference for the ecosystem.</li> <li>Create task datasets covering the breadth of Kotlin usage: the server side (Spring, Ktor), multiplatform projects (KMP), build systems (Gradle), Android, library development, and others.</li> <li>Include both mined real-world tasks and carefully designed synthetic tasks that test specific Kotlin capabilities.</li> <li>Maintain and evolve benchmarks as models improve, ensuring they remain challenging, relevant, and contamination-resistant.</li> </ul> <h2><strong>We'll be happy to have you on board if you have:</strong></h2> <ul> <li>Hands-on experience building evaluation or analysis pipelines for LLMs or AI coding agents in a research or production setting.</li> <li>Strong Python engineering skills (at least three years), with the ability to write clean, maintainable code in data-heavy and ML-adjacent codebases.</li> <li>Experience with data analysis at scale: querying large datasets (SQL/Athena), building data pipelines, and performing statistical analysis of experimental results.</li> <li>The abili

Skills