Own the measurement and improvement of model learning from tasks. Collaborate with frontier labs to design post-training recipes and data-quality techniques, run in-house evaluation systems, develop datasets and data products, assess acquired data, and build scalable ingestion and evaluation systems. The role requires production reinforcement learning experience at a frontier lab and end-to-end LLM post-training expertise.

Join a frontier AI research lab building rigorous evaluation environments and training data for advanced machine learning models. The role is intentionally flexible, allowing candidates to define how their expertise can accelerate the team. Success requires exceptional achievement in a competitive field, curiosity, speed, adaptability, and enthusiasm for teaching machines to think. This is an in-person position in San Francisco with competitive compensation, equity, benefits, meals, and relocation assistance.