Healthcare RL Engineer: Build Real-World AI Environments

BioStack Platforms; San Francisco (CA); On-site; USD 200,000 - 350,000; Full time

Benefits offered by this job

Health benefits

Meals

401(k) match

Equity

Relocation & joining bonus

Job summary

BioStack is hiring an RL Engineer to build reinforcement learning environments for healthcare AI and to run post-training experiments on language models and agents. You will transform clinical data into model-ready environments, design rewards, and evaluate multi-step agents across patient histories and medical data.

Prior healthcare experience is not required, but data judgment is critical. This is a full-time, in-person role based in San Francisco, CA, with a strong emphasis on building

Qualifications

• Experience designing RL environments with healthcare data.
• Ability to design rewards and verifiers for clinical tasks.
• Comfort coding in large ML codebases and debugging training runs.

Responsibilities

• Build healthcare-specific RL environments, including tasks, action spaces/tool interfaces, reward functions, verifiers, and evaluation harnesses.
• Run post-training experiments on language models and agents using techniques such as SFT, RLVR, RLHF/RLAIF, and reward modeling.
• Turn clinical and biomedical datasets into training environments with measurable, verifiable outcomes.
• Design rewards and verifiers that capture correctness across clinical reasoning and longitudinal decision-making tasks.
• Train and evaluate multi-step agents operating across patient histories, clinical tools, and structured/unstructured medical data.
• Build scalable pipelines for rollouts, training, evaluation, experiment tracking, and dataset iteration.
• Analyze model failures and use them to improve environments, rewards, datasets, and subsequent training runs.

Skills

Reinforcement learning

Post-training language models

Agent environments

Evaluation

Data quality assessment

Experimentation

ML systems

Healthcare data

Debugging large codebases

Tools

Python

PyTorch

Job description

BioStack is hiring an RL Engineer to build reinforcement learning environments for healthcare AI and to run post-training experiments on language models and agents. You will transform clinical data into model-ready environments, design rewards, and evaluate multi-step agents across patient histories and medical data.

Prior healthcare experience is not required, but data judgment is critical. This is a full-time, in-person role based in San Francisco, CA, with a strong emphasis on building