RL Environments Engineer - Shape AI Training Sandboxes

WeHireYou; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

Labelbox is seeking a Forward Deployed Engineer to own the design, development, and deployment of reinforcement learning environments. You will build sandboxed, reproducible execution environments that AI agents interact with during training and evaluation—terminal-based benchmarks, browser and computer-use environments, and tool-augmented workspaces.

This is a hands-on engineering role; you will write production-quality infrastructure code, integrate with open-source RL tooling, and collaborate

Qualifications

• 2+ years of professional software engineering experience.
• Strong Python fundamentals and at least one systems language (Go/Rust/C++).
• Experience with containerization and sandboxing in production.
• Familiarity with RL concepts (MDP, reward shaping, observation spaces).
• Experience building developer tooling or infra automation.
• Comfort with browser automation or terminal interaction tooling.

Responsibilities

• Design, build, and maintain sandboxed RL environments for agentic AI training.
• Develop reproducible, containerized execution environments (Docker/VMs).
• Integrate open-source agentic tooling and CLI/Harnesses to enable multi-step agent interaction.
• Build instrumentation and observability for training runs and annotations.
• Collaborate on curricula and evaluation protocols across environments.
• Own deployment, CI/CD, testing, and drift monitoring across versions.
• Prototype new environment types rapidly as requirements evolve.

Skills

Python

Go

Rust

C++

Docker

RL concepts

CLI tooling

Debugging

Tools

Docker

Podman

Firecracker

Job description

Labelbox is seeking a Forward Deployed Engineer to own the design, development, and deployment of reinforcement learning environments. You will build sandboxed, reproducible execution environments that AI agents interact with during training and evaluation—terminal-based benchmarks, browser and computer-use environments, and tool-augmented workspaces.

This is a hands-on engineering role; you will write production-quality infrastructure code, integrate with open-source RL tooling, and collaborate