Design core agent harness and execution loop for safe long-horizon tasks.
Build sandboxing, isolation, orchestration, state and workflow infra for agents.
Develop evaluation, experimentation, and debugging systems for harness issues.
Run ablations across prompts, interfaces, context, tool-use, harness behavior.
Improve observability, profiling, and diagnostics across backend, inference, GPUs.
Collaborate with research to make the harness trainable and measurable.

🎯 Requirements

Production systems in distributed infra or ML systems.
Strong Rust and Python across stacks.
Hands-on with LLM apps, coding agents, evals, and deployment.
Reliability, safety, performance, and debuggability focus.
Diagnose production issues quickly and implement durable fixes.
Collaborate with research to ship changes to production.

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot