Staff Engineer, Scalable RL Infrastructure

Vmax; San Francisco (CA); Hybrid; USD 300,000 - 500,000; Full time

Job summary

Vmax, an applied research lab, seeks an infrastructure engineer to build the systems layer for large-scale RL. You will enable researchers and ML engineers to run, debug, and reproduce experiments across thousands of GPUs, with a focus on reliability and scalability.

The role emphasizes end-to-end ownership, from architecture to deployment, and collaboration with researchers to translate complex workflows into durable platforms.

Qualifications

• Strong software engineering skills and ability to translate messy experimental workflows into durable infrastructure.
• Experience building infrastructure for LLM inference and RL training.
• Familiarity with GPU clusters, distributed training, model serving, or high-throughput inference systems.
• Knowledge of vLLM, SGLang and modern LLM-RL training frameworks.
• Ability to design reliable, observable, well-tested systems for large-scale experiments.

Responsibilities

• Build infrastructure for distributed RL training and inference across thousands of GPUs.
• Improve the reliability, debuggability, and throughput of RL experiments.
• Build interfaces that allow researchers and applied ML engineers to launch, inspect, compare, and reproduce experiments easily.
• Own infrastructure projects end to end, from architecture and implementation through deployment, documentation, and long-term maintenance.
• Identify and eliminate bottlenecks in training, rollout generation, eval execution, data movement, and cluster utilization.
• Maintain engineering standards for RL infrastructure, including testing, observability, versioning, and reproducibility.

Skills

Strong software engineering

Distributed training

Collaboration with researchers

System reliability

Debugging and performance optimization

Tools

vLLM

SGLang

LLM-RL training frameworks

Observability tools

Job description

Vmax, an applied research lab, seeks an infrastructure engineer to build the systems layer for large-scale RL. You will enable researchers and ML engineers to run, debug, and reproduce experiments across thousands of GPUs, with a focus on reliability and scalability.

The role emphasizes end-to-end ownership, from architecture to deployment, and collaboration with researchers to translate complex workflows into durable platforms.