Staff Engineer, RL & Scalable Infrastructure

Aptiora; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Aptiora is building and maintaining large-scale RL and agent-evaluation platforms used by Perplexity to train state-of-the-art models and optimize agent harnesses.

We are seeking engineers who have shipped distributed systems for compute-intensive workloads, are proficient in Python, Rust, C++, or Go, and have experience with cloud infrastructure and Kubernetes. A background in RL or ML infra is a strong plus.

Qualifications

• Experience building and shipping distributed systems for compute-intensive workloads with reliability, scalability, and performance focus.
• Proficiency in Python, Rust, C++, or Go; experience with cloud infra and container orchestration (AWS, Kubernetes).
• Familiarity with RL, agent evaluation, or ML infrastructure; interest in accelerating experimentation and model development.
• BS/MS/PhD in CS/Engineering or related field, or equivalent practical experience.

Skills

Distributed systems

Backend languages

Education

Bachelor/Master/PhD in CS/Engineering

Tools

AWS

Kubernetes

Container orchestration

Job description

Aptiora is building and maintaining large-scale RL and agent-evaluation platforms used by Perplexity to train state-of-the-art models and optimize agent harnesses.

We are seeking engineers who have shipped distributed systems for compute-intensive workloads, are proficient in Python, Rust, C++, or Go, and have experience with cloud infrastructure and Kubernetes. A background in RL or ML infra is a strong plus.