RL Engineer

BioStack builds RL environments and post-training systems for healthcare AI — tasks, rewards, verifiers, benchmarks, and agent environments for clinical reasoning, longitudinal care, and diagnostic decision-making. Hands-on role covering the full RL loop: environment/reward design, training, evaluation, iteration. No prior healthcare experience required. Looking for someone with 2+ years in RL, post-training, agents, or related ML systems, strong judgment on data quality, and comfort in a fast-moving, high-ownership startup environment.