RL Research Scientist - Post-Training on LLMs & Code Models

AMD; Santa Clara (CA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Benefits at a glance

Job summary

AMD is hiring an AI Research Scientist specializing in reinforcement learning for post-training and interactive learning of large generative models applied to engineering and hardware tasks. You will design RL algorithms, run studies, and collaborate with infra and product teams to land methods that improve task success and stability.

The role requires a PhD (preferred) and a strong publication record, with hands-on experience training RL or preference-based models at scale, especially with LLMs

Qualifications

• PhD in Computer Science, Machine Learning, or related field strongly preferred.
• Strong publication record in reinforcement learning.
• Hands‑on experience training RL or preference‑based models at non‑trivial scale (GPUs, distributed jobs).
• Experience with LLM post‑training, RLHF/RLAIF, or policy optimization for language or code agents.

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

RL research

RLHF/RLAIF

Education

PhD in CS/ML

Tools

GPUs

Distributed training

Job description

AMD is hiring an AI Research Scientist specializing in reinforcement learning for post-training and interactive learning of large generative models applied to engineering and hardware tasks. You will design RL algorithms, run studies, and collaborate with infra and product teams to land methods that improve task success and stability.

The role requires a PhD (preferred) and a strong publication record, with hands-on experience training RL or preference-based models at scale, especially with LLMs