RL Sandbox Engineer: Build Robust Training Environments

FDE Times; San Angelo (TX); On-site; USD 140,000 - 200,000; Full time

Job summary

Labelbox is hiring a Forward Deployed Engineer to own the design, development, and operationalization of reinforcement learning environments. You will build sandboxed, reproducible execution environments that AI agents interact with during training and evaluation, including terminal emulators, browser automation, and tool‑augmented workspaces.

This is a hands‑on engineering role writing production‑quality infrastructure code, integrating with open‑source RL tooling, and ensuring environments are

Qualifications

• 2+ years of professional software engineering experience.
• Proficiency in Python and at least one systems-level language (Go, Rust, C++).
• Experience with containerization and sandboxing (Docker/Podman/Firecracker) in production or near-production contexts.
• Familiarity with RL concepts (MDPs, reward shaping, episode structure).
• Experience building developer tooling, CLI tools, or infrastructure automation.
• Comfort with browser automation frameworks or terminal interaction tooling.

Responsibilities

• Design, build, and maintain sandboxed RL environments for agentic AI training.
• Develop reproducible, containerized execution environments for deterministic task rollouts.
• Integrate open‑source tooling and custom harnesses for multi‑step agent interaction.
• Build instrumentation and observability layers for clean training data and auditability.
• Collaborate with data operations to design curricula and evaluation protocols.
• Own environment deployment, CI/CD pipelines, and monitoring for drift.

Skills

Python

Systems languages

RL concepts

Dev tooling

Browser automation

Tools

Docker

Podman

Firecracker

Job description

Labelbox is hiring a Forward Deployed Engineer to own the design, development, and operationalization of reinforcement learning environments. You will build sandboxed, reproducible execution environments that AI agents interact with during training and evaluation, including terminal emulators, browser automation, and tool‑augmented workspaces.

This is a hands‑on engineering role writing production‑quality infrastructure code, integrating with open‑source RL tooling, and ensuring environments are