Principal AI Research Scientist Post-Training · Alignment · Reinforcement Learning Autodesk AI Lab: London · San Francisco · Toronto · Remote (US/CA/EU
Autodesk
San Francisco, London, Toronto, Boston, New York, Plano
Workplace: RemoteFull timeFunction: Data Science & Machine LearningEducation: phdSkills: ["Reinforcement learning","RLHF","PPO","RLAIF","Post-training","Alignment","Evaluation","Long-horizon reasoning","Neural networks"]Lead post-training reinforcement learning research for foundation models, aligning behavior with long-horizon reasoning and real-world workflows. Develop novel post-training algorithms, design robust evaluation frameworks, and drive scalable, reproducible workflows while collaborating with infrastructure and publishing impactful research.
