Lead RL Scientist for LLM Post-Training & Code Models

AMD; Santa Clara (CA); On-site; USD 130,000 - 160,000; Full time

Benefits offered by this job

Comprehensive benefits package

Job summary

AMD in Santa Clara seeks a Lead AI Research Scientist specialized in reinforcement learning. You will advance post-training algorithms and work on engineering tasks with cutting-edge technology. This role requires a PhD in relevant fields and a strong publication record.

The position promises significant engagement with empirical studies and collaboration with infra teams to enhance AI solutions. You’ll be at the forefront of innovation in a supportive and inclusive environment at AMD.

Qualifications

• Strong publication record in reinforcement learning or closely related fields.
• Hands-on experience in training RL models at scale.
• Experience in LLM post-training algorithms.

Responsibilities

• Research RL methods for post-training LLMs on structured tasks.
• Design training recipes suited to sparse or expensive feedback.
• Characterize failure modes and propose mitigations.
• Collaborate with engineers to scale training.
• Publish at top venues and lead the internal RL roadmap.

Skills

Reinforcement Learning

Machine Learning

Empirical Studies

Algorithm Development

Publication Record

Education

PhD in Computer Science or related field

Job description

AMD in Santa Clara seeks a Lead AI Research Scientist specialized in reinforcement learning. You will advance post-training algorithms and work on engineering tasks with cutting-edge technology. This role requires a PhD in relevant fields and a strong publication record.

The position promises significant engagement with empirical studies and collaboration with infra teams to enhance AI solutions. You’ll be at the forefront of innovation in a supportive and inclusive environment at AMD.