Labelbox
Forward Deployed Engineer, RL Environments
About this role
Labelbox is seeking a Forward Deployed Engineer to design and build sandboxed reinforcement learning environments where AI agents train and evaluate. You'll develop production infrastructure for terminal-based tasks, browser automation, and computer-use simulators, working closely with data operations to ensure robustness and observability.
What you'll do
- Design and maintain sandboxed RL environments for agentic AI training including terminal emulators, browser automation, and computer-use simulators
- Develop reproducible, containerized execution environments with deterministic task rollouts and reward signal collection
- Build instrumentation and observability layers for trajectory capture, logging, and state snapshotting
- Integrate with open-source agentic tooling and custom CLI/API harnesses for multi-step agent interaction
- Own environment deployment reliability including CI/CD pipelines, automated testing, and version monitoring
- Rapidly prototype new environment types as requirements evolve
What they're looking for
- Python and systems languages (Go, Rust, C++)
- Containerization and sandboxing (Docker, Podman, Firecracker)
- Reinforcement learning concepts (MDPs, reward shaping, observation/action spaces)
- Developer tooling and infrastructure automation
- Browser automation and terminal interaction frameworks
- Debugging across process boundaries and container layers
- Reading and implementing from academic papers and open-source repositories
Benefits
- Work at the cutting edge of AI development with industry leaders
- High-impact environment with expanded responsibilities and rapid career growth
- Clear ownership and autonomy with explicit metrics
- Fast-paced startup culture rewarding high agency and execution
- Continuous learning surrounded by experts solving frontier AI problems
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Labelbox
Labelbox builds AI infrastructure and data solutions that enable enterprise customers to train, evaluate, and deploy frontier AI models and agents. The company is hiring Forward Deployed Engineers, Applied Research Engineers, and Associate engineers to work directly with AI labs on data pipelines, reinforcement learning environments, and agent development systems.
- Website
- labelbox.com
Likely interview questions
- Walk us through a time you designed and deployed a containerized system in production. What were the key reliability challenges, and how did you handle debugging across container boundaries?
- Describe your experience with browser automation or terminal interaction tooling. What frameworks have you used, and what were the trickiest parts to get right?