Senior/Staff Applied AI Engineer, Agent Harness

Headcount: 1

Job Details

• Experience: 4+ years
• Salary: Not specified
• Equity: 1%–2%
• Visa sponsorship: H-1B, O-1, OPT
• Employment type: Full-time
• Work arrangement: In person, 5 days a week, at our San Francisco office

Benefits & Perks

• Meals in the office
• Health insurance
• Unlimited PTO

About the Role

This role builds the layer that turns model capability into systems that work for users. You’ll develop the core agent harness—including the execution loop, tool-use strategies, context construction, and model-facing experimentation—and iterate on agent behaviors across real customer workflows and long-horizon tasks.

A defining stance: the creative step happens once, at authoring. What executes afterward is deterministic, compiled, type-checked code rather than stochastic tool-chaining. You’ll own the boundary between what the model decides at runtime and what ships as code.

You’ll build and run evaluations against replicas of real customer environments, reliable enough to gate releases; analyze production failures and attribute them to the right layer (model, prompt, tool contract, environment state, or retry logic); and extend the computer-use agent to systems with no API. You’ll own the guarantees that make it production-ready: a fresh microVM per task, credentials injected at session start and never seen by the model, every action recorded, and any session killable mid-run.

What You’ll Own

• The core agent harness: execution loop, tool-use strategies, context construction, and model-facing experimentation
• Agent behaviors across real customer workflows and long-horizon tasks
• The boundary between runtime model decisions and deterministic, compiled, type-checked execution
• Evaluations against replicas of real customer environments, reliable enough to gate releases
• Production failure analysis and systematic robustness improvements, attributed by layer
• Extending computer use to API-less systems, with production guarantees: a per-task microVM, credentials hidden from the model, full action recording, and killable sessions
• Feedback loops and data systems that bring better real-task data into evaluation and training

Requirements

• Experience with agent frameworks or tool-using LLM systems
• Enjoy debugging messy, real-world failures and turning them into improvements
• Interest in building the layer that turns model capability into systems that work for users
• Python/TypeScript and modern AI tooling
• Experience with evaluations, fine-tuning, and prompt design
• Ability to own systems end to end
• Systems and user-outcome thinking