RL Infra Engineer: Scale GPU RL Experiments (Equity)

Aionia Group; San Francisco (CA); On-site; USD 300,000 - 500,000; Full time

Job summary

Aionia Group in San Francisco is seeking a Systems Infrastructure Engineer to build scalable infrastructure for RL experiments. This role offers a unique opportunity to work on innovative projects with leading researchers in a well-funded AI company.

The ideal candidate has over 2 years of experience in RL systems, a degree in a related field, and a passion for scalable solutions. Competitive compensation includes a base salary of $300K–$500K plus equity.

Qualifications

• 2+ years building infrastructure for LLM or RL systems.
• Experience at a high-engineering-bar organization.
• Experience with GPU clusters, distributed training, and high-throughput inference systems.

Responsibilities

• Design and deploy infrastructure for distributed RL training and inference.
• Improve reliability and throughput for large-scale RL experiments.
• Establish engineering standards for RL infrastructure.

Skills

Building infrastructure for LLM or RL systems

Hands-on experience with GPU clusters

Familiarity with modern LLM-RL training frameworks

Curiosity and hypothesis-driven thinking

Education

Degree in CS, EECS, Mathematics, or a related field

Tools

vLLM

SGLang

veRL

SkyRL

DeepSpeed

Job description

Aionia Group in San Francisco is seeking a Systems Infrastructure Engineer to build scalable infrastructure for RL experiments. This role offers a unique opportunity to work on innovative projects with leading researchers in a well-funded AI company.

The ideal candidate has over 2 years of experience in RL systems, a degree in a related field, and a passion for scalable solutions. Competitive compensation includes a base salary of $300K–$500K plus equity.