Staff Software Engineer, RL Environments

What you'll do

• Design platform capabilities for sandboxed execution, environment packaging and versioning, rollout orchestration, trajectory capture, verifiers, and environment authoring.
• Build and instrument RL environments, task suites, and graders that expose capability gaps and provide reliable reward signals.
• Set technical direction across teams while delivering hands-on engineering work.

What they ask for

• 8+ years of software engineering experience; strong fundamentals in distributed systems, system design, data structures, and algorithms.
• Strong Python skills and production software experience, plus comfort with another stack area such as TypeScript/React, Go, or Rust.
• Deep experience with containerization and sandboxed execution, and experience building or operating high-throughput backend systems.
• Hands-on experience building with LLMs, including agent loops, tool calling, MCP, or eval harnesses.

Nice to have

• Experience building RL environments, agentic benchmarks, or eval harnesses; familiarity with post-training methods and reward-signal failure modes.
• Experience with RL training or serving stacks, cloud-native infrastructure, high-scale sandboxing, observability, or research-adjacent engineering.

Pay

$252,000 — $315,000 USD (base salary)

Tools

Python, TypeScript/React, Go, Rust, Docker, VMs, gVisor/Firecracker, Kubernetes

AI focus

Build reinforcement learning environments, benchmarks, verifiers, and reward signals; work with LLM agents and model training and evaluation.