RL Research Scientist for LLM Post-Training & Code Models

AMD; Santa Clara (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

AMD benefits

Job summary

AMD in Santa Clara, CA is seeking an AI Research Scientist, Reinforcement Learning (LLM) and Post-Training to push RL methods for large generative models used in engineering tasks. You will design reward models, run empirical studies, and partner with infra and product teams to land robust, scalable approaches.

You should have a PhD and a strong publication record, with hands-on experience training RL or preference-based models at scale using GPUs and distributed systems.

Qualifications

• PhD in Computer Science, Machine Learning, or related field strongly preferred.
• Strong publication record in reinforcement learning or closely related ML areas.
• Hands-on experience training RL or preference‑optimized models at non-trivial scale (GPUs, distributed jobs).

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.

Skills

RL theory

Publication record

GPUs

Distributed training

Education

PhD in CS/ML

Tools

LLMs

RLHF

Job description

AMD in Santa Clara, CA is seeking an AI Research Scientist, Reinforcement Learning (LLM) and Post-Training to push RL methods for large generative models used in engineering tasks. You will design reward models, run empirical studies, and partner with infra and product teams to land robust, scalable approaches.

You should have a PhD and a strong publication record, with hands-on experience training RL or preference-based models at scale using GPUs and distributed systems.