Senior/Staff Reinforcement Learning Engineer - Machine Learning Research & Development

About us

Kaiko is actively developing a next-generation autonomous clinical AI assistant that aids clinicians in reasoning across patient data, guidelines, and diagnostics. The company works closely with leading hospitals and research centers, including the Netherlands Cancer Institute, to develop specialized diagnostic agents and ensure safe operation in clinical settings.

Job description

As a senior/staff RL engineer - ML R&D, you will own the RL training infrastructure end-to-end, managing the distributed training stack, reward pipelines, and experiment infrastructure. You will tackle complex challenges such as reward hacking and objective-level instability, while also exploring new algorithms and bringing effective solutions into production. Your role is crucial in ensuring the alignment and reasoning capabilities of our AI systems, directly impacting healthcare outcomes.

• Build and maintain reward pipelines: verifiable reward signals, LLM-based reward models, and reward shaping strategies for complex clinical reasoning tasks
• Own the RL training stack end-to-end and keep it scaling cleanly across large MoE models and long contexts
• Debug training instabilities at root cause — reward hacking, entropy collapse, credit assignment failures, gradient issues — and ship fixes, not workarounds
• Explore new RL algorithms and reward designs; run controlled experiments and translate promising results into the main training stack
• Scale runs across more nodes, longer contexts, and more complex parallelism as models and tasks grow
• Contribute upstream to open-source frameworks when you find bugs or missing features

Relevant work experience

• Deep hands-on experience with RL training systems: you have shipped and scaled RL or post-training runs, not just run tutorials
• Fluent in at least one distributed training framework at a level where you can read the source and debug silent failures
• Strong understanding of core RL challenges: reward hacking, credit assignment, exploration, entropy collapse, sample efficiency — and practical ways to address them
• Comfortable at the intersection of research and engineering: you read papers, implement ideas, and know when something is worth productionising
• Excellent software engineering: clean Python, typed code, reproducible experiments, good test coverage
• Independent operator: you don't need prescribed task lists; you take a system from 'running' to 'stable, fast, and understood.'

Benefits

Skills required for the job