Staff Engineer, Scalable RL Infrastructure

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

Job summary

Inception is seeking engineers and scientists to design, optimize, and maintain core systems enabling scalable reinforcement learning for large models. You will work at the intersection of research and systems engineering, optimizing rollout and reward pipelines, improving reliability, observability, and orchestration, and ensuring production-readiness.

Responsibilities include building infrastructure for RL workloads, boosting training throughput, and creating shared tooling for monitoring and

Qualifications

• Understanding of RL systems from a systems perspective.
• Experience with large-scale ML workflows and orchestration.
• Familiarity with reliability, observability, and production readiness.

Responsibilities

• Design, build, and optimize infrastructure for large-scale RL workloads.
• Improve reliability and throughput of RL training pipelines.
• Develop monitoring and observability tools for high uptime and debuggability.

Skills

RL systems

Distributed systems

Observability

Orchestration

Education

BS/MS/PhD in CS/Engineering

Tools

Docker

Kubernetes

CI/CD

Job description

Inception is seeking engineers and scientists to design, optimize, and maintain core systems enabling scalable reinforcement learning for large models. You will work at the intersection of research and systems engineering, optimizing rollout and reward pipelines, improving reliability, observability, and orchestration, and ensuring production-readiness.

Responsibilities include building infrastructure for RL workloads, boosting training throughput, and creating shared tooling for monitoring and