Drimva

Labelbox

Member of Technical Staff

$140K–$200K

San Francisco Bay Area · Staff · Full-time · Posted Sep 22, 2026

Experience
2+ years of professional software engineering experience.

About the job

Build and operate reliable, sandboxed environments and infrastructure for training and evaluating agentic AI with reinforcement learning.

What you'll do

  • Design and maintain RL environments such as terminal, browser, and computer-use workspaces; build reproducible, containerized execution and agent tooling.
  • Develop logging, trajectory capture, testing, deployment, and monitoring to keep environments observable and reliable.
  • Work with data operations on task curricula and evaluation protocols, and prototype new environment types.

What they ask for

  • 2+ years of professional software engineering experience; strong Python fundamentals and proficiency in at least one of Go, Rust, or C++.
  • Experience with containerization and sandboxing, such as Docker, Podman, or Firecracker, in production or near-production contexts.
  • Familiarity with RL concepts and experience building or maintaining developer tooling, CLI tools, or infrastructure automation.
  • Comfort with browser automation or terminal interaction tooling; strong debugging skills and ability to implement from papers and open-source repositories.

Nice to have

  • Direct experience building RL environments or agentic AI evaluation frameworks.
  • Familiarity with GCP or AWS infrastructure; prior work at an AI data, ML platform, or research organization, or relevant open-source contributions.

Pay

$140,000 — $200,000 USD (annual base salary)

Tools

Python, Go, Rust, C++, Docker, Podman, Firecracker, GCP

AI focus

Build sandboxed environments, tooling, and evaluation infrastructure for reinforcement-learning training and evaluation of agentic AI.

Model-written summary · the original posting is authoritative

First seen Oct 10, 2026 · Last verified Nov 5, 2026 (UTC)