Forward-Deployed RL Environments Engineer

Forward Deployed Engineer, RL Environments; San Francisco (CA); On-site; USD 140,000 - 200,000; Full time

Job summary

Labelbox in San Francisco is seeking a Forward Deployed Engineer to design, build, and operate reinforcement learning environments used to train and evaluate AI agents. You’ll create sandboxed, reproducible environments and integrate with open-source RL tooling, ensuring robustness and observability for human annotators and model agents alike.

This is a hands-on role focused on ownership, rapid prototyping, and collaboration with data operations.

Qualifications

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

Responsibilities

• Design, build, and maintain sandboxed RL environments (terminal emulators, browser automation harnesses, etc.).
• Develop reproducible, containerized execution environments (Docker, VMs) for deterministic task rollouts.
• Integrate with open-source agentic tooling and custom harnesses for multi-step agent interaction.
• Build instrumentation and observability layers for clean, auditable training data.
• Collaborate with data operations to design task curricula and evaluation protocols.
• Own environment deployment, CI/CD pipelines, and monitoring for drift across versions.
• Prototype new environment types quickly as requirements evolve.

Skills

Python

Go/Rust/C++

Containerization

Sandboxing

RL concepts (MDPs)

Developer tooling/CLI

Browser/terminal automation

Debugging across processes

Reading papers/open-source benchmarks

Tools

Docker

Podman

Firecracker

Job description

Labelbox in San Francisco is seeking a Forward Deployed Engineer to design, build, and operate reinforcement learning environments used to train and evaluate AI agents. You’ll create sandboxed, reproducible environments and integrate with open-source RL tooling, ensuring robustness and observability for human annotators and model agents alike.

This is a hands-on role focused on ownership, rapid prototyping, and collaboration with data operations.