RL Infra Intern: Post-Training for LLMs & Multimodal AI

AMD; Santa Clara (CA); Hybrid; USD 167,000 - 212,000; Full time

Benefits offered by this job

AMD benefits at a glance

Mentorship program

Professional development opportunities

Job summary

AMD is seeking a PhD candidate for a Summer 2027 Internship/Co-op in Santa Clara, CA. You will develop and optimize infrastructure for RL-based post-training of large language and multimodal models, build scalable systems for rollout, inference, and policy updates, and collaborate with researchers to translate requirements into production-quality infrastructure.

You will work onsite or in a hybrid setting, contributing to reproducibility, profiling pipelines, and documenting designs for

Qualifications

• PhD candidate in CS/ML/AI/CE.
• Strong Python and PyTorch experience.
• Experience with distributed training and large-scale inference.
• Familiarity with multi-GPU workloads and cluster environments.

Responsibilities

• Develop and optimize infrastructure for RL-based post-training of large language and multimodal models.
• Build scalable systems for rollout generation, inference, reward computation, and policy updates.
• Improve distributed training efficiency, reliability, fault tolerance, and resource utilization.
• Design interfaces that enable researchers to implement and evaluate new RL algorithms quickly.
• Build tools for experiment configuration, checkpointing, logging, monitoring, and reproducibility.
• Profile end-to-end training pipelines and resolve performance, memory, and communication bottlenecks.
• Support on-policy and off-policy training workflows using verifiable feedback.
• Collaborate with researchers to translate experimental requirements into production-quality infrastructure.
• Document system designs and contribute to technical reports and publications.

Skills

Python

RL knowledge

Distributed training

GPU memory management

Cluster environments

Education

PhD candidate in CS/ML/AI/CE

Tools

PyTorch

Containerization

Experiment tracking

Job description

AMD is seeking a PhD candidate for a Summer 2027 Internship/Co-op in Santa Clara, CA. You will develop and optimize infrastructure for RL-based post-training of large language and multimodal models, build scalable systems for rollout, inference, and policy updates, and collaborate with researchers to translate requirements into production-quality infrastructure.

You will work onsite or in a hybrid setting, contributing to reproducibility, profiling pipelines, and documenting designs for