Platform Engineer, RL & Eval Data | 100% remote
Core
Build and maintain scalable platforms for RL environments, evaluation harnesses, and data annotation tools for frontier AI labs.
Role type
Senior Platform Engineer (RL & Eval Data)
Builds
RL environments, evaluation platforms, annotation tooling, and infrastructure for LLM agent training
Domain
AI/ML infrastructure, Reinforcement Learning, Large Language Model evaluation
Deliverable
production ML models
Required skills
Python backend engineering, API design, Postgres, TypeScript/React, distributed systems design, job orchestration, Kubernetes, cloud providers, observability, security fundamentals, RL environment construction, sandbox infrastructure (Daytona/E2B/Modal/gVisor), evaluation harness development, LLM provider API integration, annotation tooling
Preferred skills
Open-source contributions to RL/eval frameworks, experience with large distributed contributor workforces
Technologies
Python, Postgres, TypeScript, React, Docker, Kubernetes, Daytona, E2B, Modal, gVisor, Firecracker
Responsibilities
Maintain and improve existing platform codebases, design and ship new features across the stack, scale systems for high volume, build RL environments and sandbox infrastructure, ensure reliability and security, support data teams with tooling
Seniority
Senior, hands-on IC
