Founding Research Engineer, RL & Post-Training

Higher People•San Francisco, CA

6d•Onsite

About The Position

Our client, a leader in the AI-native healthcare and drug discovery space, is looking to hire a Founding Research Engineer for RL and Post Training. They're building the data layer that turns messy real-world clinical workflows into AI-ready products for leading AI labs, human data companies, and frontier biotech teams. The long-term vision is linking real-world healthcare data with genomics, imaging, biomarkers, and experimental data to make high-quality healthcare accessible to everyone and radically accelerate drug discovery. They're backed by PeakXV, Y Combinator, Afore Capital, SV Angel, plus angels from OpenAI, Meta, and Google DeepMind.

Requirements

Excited to apply frontier RL methods to healthcare, medicine, and biological data
Experience with reinforcement learning, LM post-training, agent environments, reward modeling, evaluation, or related ML systems
Strong judgment on data quality (signal, label fidelity, coverage, longitudinal depth, clinical relevance)
Can move fast from research concept to working prototype, then iterate on empirical results
Comfortable designing controlled experiments, building baselines, and drawing trustworthy conclusions from noisy real-world data
Comfortable in large ML codebases, debugging training runs, data pipelines, eval harnesses, and model behavior
A self-starter who owns ambiguous problems and drives projects to completion
Thrives where research, engineering, product, and customer needs intersect

Nice To Haves

2+ years of experience in reinforcement learning, post-training, agents, or related ML systems
Prior healthcare experience not required

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 like 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