Research Engineer, RL/Reasoning

About BioStack

BioStack is building the data layer for AI-native healthcare and drug discovery. We work with leading AI labs, human data companies, and frontier biotech teams to source, structure, and deliver high-value clinical and preclinical datasets for model training, evaluation, and deployment.

We sit at the intersection of healthcare, frontier AI, and data infrastructure. Our work spans medical institutions, clinics, imaging centers, and data partners globally, turning messy real-world clinical workflows into AI-ready products that matter.

BioStack is backed by Y Combinator, Afore Capital, Verdict Capital, Heroic VC, and high-profile angels from Meta and Google DeepMind.

About the Role

As an RL Engineer at BioStack, you will help build the reinforcement learning infrastructure for healthcare AI.

BioStack is building the data engine and RL environment layer for medical AI systems. We source high-value clinical datasets, structure them into model-ready workflows, build benchmarks and reward functions, and create healthcare-specific environments where agents can learn to reason, decide, and improve against verifiable outcomes.

This role sits at the core of that effort. You will work on designing, training, evaluating, and scaling RL systems for real healthcare workflows, including clinical reasoning, chronic disease management, longitudinal patient care, medical data annotation, diagnostic decision-making, and biomedical research tasks.

We’re looking for someone with strong reinforcement learning and ML engineering experience, a bias toward fast iteration, and strong judgment around data. You should have good taste in what makes a dataset valuable: knowing how to evaluate signal quality, coverage, label reliability, clinical relevance, distributional diversity, failure modes, and whether a dataset can support useful RL tasks, benchmarks, and reward functions.

This is a 6-month contract role, based in San Francisco, CA. We expect this to be an in-person/hybrid role, especially for early team members working closely with the founding team.

You might thrive in this role if:

• You are excited by the idea of applying frontier RL methods to healthcare, medicine, and biological data.
• You have experience with reinforcement learning, language model post-training, agent environments, reward modeling, evaluation, or related ML systems.
• You have strong taste in data: you can look at a dataset and quickly assess whether it is useful, noisy, biased, underpowered, poorly labeled, or capable of supporting meaningful model improvement.
• You can evaluate datasets for signal quality, clinical relevance, label fidelity, longitudinal depth, coverage, edge cases, and suitability for RL environments.
• You can move quickly from research concept to working prototype, then iterate based on empirical results.
• You are comfortable designing controlled experiments, building baselines, and drawing trustworthy conclusions from noisy real-world data.
• You like working with complex datasets, including clinical notes, labs, imaging, ECGs, longitudinal patient histories, and expert annotations.
• You are comfortable working in large ML codebases and can debug training runs, data pipelines, eval harnesses, and model behavior.
• You care about building systems that are technically rigorous, clinically grounded, and useful beyond demos.
• You are a self-starter who can own ambiguous problems, define the right technical path, and drive projects to completion.
• You thrive in a fast-moving startup environment where research, engineering, product, and customer needs all intersect.