AI Research Scientist, Reinforcement Learning (LLM) and Post-Training

AMD is a technology company advancing processors, artificial intelligence, and related technologies. The AI Research Scientist will develop and analyze reinforcement learning methods for post-training large language and code models on demanding engineering tasks, design reward systems and training strategies, investigate failure modes, and collaborate with infrastructure teams to scale and deploy research. The role also includes publishing research and providing technical leadership for the reinforcement learning roadmap.

Responsibilities:

• Research and develop RL methods for post-training LLMs and code models on structured engineering tasks with verifiable or preference-based feedback
• Design reward models, curricula, and off-policy or on-policy training recipes suited to sparse, noisy, or expensive labels from experts and simulators
• Characterize failure modes (reward hacking, degenerate policies, instability) and propose mitigations grounded in experiments
• Collaborate with RL infra engineers to scale training; define interfaces for rollout generation, logging, and reproducibility
• Publish at top venues (e.g. NeurIPS, ICML, ICLR) and contribute internal technical leadership on the RL roadmap