# Forward Deployed Engineer, RL Environments

Hiring organization: [Labelbox](https://career.thegoodapps.co/organizations/labelbox)

Canonical page: https://career.thegoodapps.co/jobs/44b0f238-0f5e-4e1d-baac-8364798edb71

Listed on Labelbox's own careers site. Applications go to them directly.

- Employment type: full time
- Location: San Francisco, CA
- Salary: 140000 – 200000 USD per year

## Summary

This role owns the design and operationalization of reinforcement learning training environments—the sandboxed systems where AI agents learn and interact. It's ideal for a systems-minded software engineer who understands RL fundamentals and wants to solve high-leverage infrastructure problems at the intersection of ML and DevOps.

_Our summary, not Labelbox's wording._

## Skills named

Amazon ECS, Amazon EKS, Amazon Web Services (AWS), C++, Docker, Go, Podman, Python, Rust

## Required

- 2+ years professional software engineering experience
- Strong Python fundamentals
- At least one systems-level language (Go, Rust, or C++)
- Production containerization and sandboxing experience (Docker, Podman, Firecracker or similar)
- Understanding of RL concepts: MDPs, reward shaping, episode structure, observation/action spaces
- Experience building or maintaining developer tooling, CLI tools, or infrastructure automation
- Comfort with browser automation or terminal interaction tooling
- Strong debugging across process boundaries and container layers
- Ability to implement from academic papers and open-source benchmarks independently

## Nice to have

- Direct experience building RL environments (Gymnasium/Gym, PettingZoo, or custom implementations)
- Experience with agentic AI evaluation frameworks (SWE-bench, WebArena, OSWorld, TerminalBench)
- GCP or AWS infrastructure experience
- Prior work at AI data, ML platform, or AI research lab
- Open-source contributions in RL, agents, or dev-tools

Apply on Labelbox's site: https://job-boards.greenhouse.io/labelbox/jobs/5101187007