Member of Technical Staff
Core
Design, build, and maintain sandboxed reinforcement-learning environments for agentic AI training, including terminal emulators, browser automation harnesses, and tool-augmented workspaces.
Role type
Senior IC software engineer (RL environments & agentic AI tooling)
Builds
Containerized execution environments, CLI/API harnesses, and observability systems for deterministic task rollouts and reward collection
Domain
Artificial Intelligence / Reinforcement Learning / Systems Engineering
Deliverable
production ML models
Required skills
Python, Go/Rust/C++, containerization (Docker/Podman/Firecracker), reinforcement learning concepts (MDPs, reward shaping), CLI/API development, debugging across process boundaries, implementing academic papers
Preferred skills
RL environments (Gymnasium/Gym, PettingZoo), agentic-AI evaluation frameworks (SWE-bench, WebArena, OSWorld, TerminalBench), cloud infrastructure (GCP/AWS)
Technologies
Docker, Podman, Firecracker, Python, Go, Rust, C++, CI/CD pipelines
Responsibilities
Develop reproducible, containerized execution environments; Integrate and extend open-source agentic tooling; Build observability and instrumentation for structured logging and trajectory capture; Partner with data operations on task curricula and evaluation protocols; Own environment deployment and reliability through CI/CD pipelines; Rapidly prototype and deliver new environment types
Seniority
Mid-level, hands-on IC