Apply on Employer Site

Code Metal · 4 months ago

Reinforcement Learning Engineer

San Francisco, CA

Full-time

Hybrid

Entry, Mid Level

2+ years exp

Code Metal AI is a pioneering company focused on large language models and code generation. The role involves building and maintaining distributed training systems, designing scalable data pipelines, and driving innovation in reinforcement learning solutions.

Artificial Intelligence (AI)Information TechnologySoftware

No H1B

Security Clearance Required

U.S. Citizen Only

Responsibilities

Build and maintain robust distributed training systems using PyTorch (2+ years experience required)

Design and implement scalable data curation and quality assurance pipelines to ensure top-tier training datasets

Develop orchestration tools that manage complex workflows across large-scale AI model training and evaluation

Drive innovation by developing evaluation frameworks and reinforcement learning solutions, including recent advancements in Reinforcement Learning with Human Feedback (RLHF)

Engage with frontier research through open-source projects and potential publications, applying RLHF to Large Language Models (LLMs), ideally focusing on code generation tasks

Qualification

PyTorchReinforcement LearningData CurationQuality Assurance PipelinesEvaluation FrameworksDistributed TrainingOrchestration ToolsOpen-source ContributionsResearch ExperienceSynthetic Data Generation