Member of Technical Staff - RL Infrastructure

What you'll do

• Build infrastructure for distributed RL training and inference across thousands of GPUs; improve experiment reliability, debuggability, and throughput.
• Develop researcher-facing tools to launch, inspect, compare, and reproduce experiments, and own infrastructure projects from design through maintenance.
• Identify bottlenecks and maintain standards for testing, observability, versioning, and reproducibility.

What they ask for

• Strong software engineering experience.
• Experience building infrastructure for LLM inference and/or RL training, and experience with GPU clusters, distributed training, model serving, or high-throughput inference systems.
• Familiarity with vLLM, SGLang and modern LLM-RL training frameworks.
• Strong understanding of reliability, observability, testing, debugging, and performance optimization; experience building tools, platforms, or services for technical users.

Nice to have

• Experience supporting research or fast-moving ML teams.
• Evidence of independent technical work or experience reducing operational complexity in brittle, slow, or hard-to-debug systems.

Pay

$300,000 - $500,000 USD (base salary)

Tools

vLLM, SGLang

AI focus

Build infrastructure for large-scale RL training, inference, rollouts, evaluations, and experiments.