Member of Technical Staff - Environments & Post-Training

**About Hillclimb** ------------------- Hillclimb works with the world's best researchers, scientists, and engineers to teach AI to think like them so that it has the means to improve itself. We're a founding team of former DeepMind \& quant researchers backed by Garry Tan, Jeff Dean, Tier 1 VCs \& angel investors from OpenAI, Anthropic, DeepMind, SpaceXAI \& Meta Superintelligence Labs. We achieved SOTA for math shortly after graduating YC. **About this role:** -------------------- You're work will consist of the following and many more: * Turn ML research problems into environments that reward a model for real progress and good research taste * Test whether each environment's reward is repeatable and tracks the quality of the work it scores * Build systems that create environments at scale and catch broken ones before they reach training * Run post\-training experiments to find which environments are trainable **Preferred Experience:** ------------------------- * Experience with LLMs, RL, RLHF/RLAIF, RLVR, post\-training, evals, graders, synthetic data, model training, or coding agents * Understanding of what makes a reward evaluation trustworthy, and how models exploit one that is not * Previous experience in designing automated systems for building, validating, and quality checking environments. **Benefits:** ------------- * Extremely competitive salary and equity * Health, Dental, Vision insurance * Competitive 401k match * Free lunch and dinner