Senior Research Engineer (Agentic Behavior)

📋 Description

• Build tools to capture and analyze errors in AI Kotlin code generation.
• Create observability pipelines over agent traces in JetBrains IDEs and other agents.
• Design evaluation pipelines for Kotlin code gen quality across metrics.
• Build simulation environments for Kotlin dev tasks (Gradle, Spring, etc.).
• Own evaluation infrastructure: metrics, experiments, regression checks.
• Collaborate with model providers to improve Kotlin models.

🎯 Requirements

• Hands-on experience building eval/analysis pipelines for LLMs/AI agents in research or prod.
• Strong Python engineering (≥3 years), clean, data/ML-adjacent codebase.
• Experience with data analysis at scale: SQL/Athena, data pipelines, stats of experiments.
• Own projects end to end: identify problems, design eval, run experiments, ship fixes.
• Product-aware mindset: translate real failure modes into eval/training work.
• Familiarity with Kotlin or willingness to learn deeply (daily Kotlin code).

🎁 Benefits

• Strong base salary
• Flexible work location
• Remote work up to 30 days per year abroad
• Relocation support
• Learning and development opportunities
• Mental health support