Founding Harness Engineer

Wwshemi; San Francisco (CA); On-site; USD 180,000 - 220,000; Full time

Benefits offered by this job

Founding equity

Job summary

Wwshemi in San Francisco, CA is hiring to build the runtime and safeguards for an AI coworker that assists teams. You will design the agent runtime, handle context gathering, tool selection, and task completion while refining system prompts for reliable, safe initiative.

You will implement safety gates, multi-tenant data separation, and evaluation tests, working directly with the founding team to shape a practical product. This on-site role requires Bay Area residency or relocation.

Qualifications

• Production experience shipping tool-using LLM agents
• Hands-on system prompt design and testing
• Experience building evaluation and regression test harnesses
• Understanding safe tool execution and multi-user data risks
• Strong ownership and ability to explain technical tradeoffs
• Experience with LLM agents, tool use, evaluation, and prompt engineering

Responsibilities

• Design and build the agent runtime for context gathering, deciding when to act, tool selection, approval, and task completion
• Write and refine system prompts to encourage useful initiative without noisy or risky behavior
• Build evaluation and regression tests for real tasks, tool use, and failure cases, and catch regressions as prompts change
• Improve reliability across long-running work, interruptions, and retries
• Implement safety boundaries, including approval gates and multi-tenant data separation
• Work directly with the founding team and early users to shape the product

Job description

This listing's locations On-site - San Francisco, California, United States

Employment Full-time

Workplace On site

Compensation USD 200000 (period not stated)

Join an early-stage AI company building an AI coworker for teams. You will develop the runtime and safeguards that help AI agents take useful initiative, work reliably, and handle real tasks safely.

What You'll Do

• Design and build the agent runtime for context gathering, deciding when to act, tool selection, approval, and task completion.
• Write and refine system prompts to encourage useful initiative without noisy or risky behavior.
• Build evaluation and regression tests for real tasks, tool use, and failure cases, and catch regressions as prompts change.
• Improve reliability across long-running work, interruptions, and retries.
• Implement safety boundaries, including approval gates and multi-tenant data separation.
• Work directly with the founding team and early users to shape the product.

What We're Looking For

• Production experience shipping tool-using LLM agents, beyond demos or thin prompt wrappers.
• Hands‑on system prompt design, with iterative testing and improvement.
• Experience building evaluation and regression test harnesses for LLM or agent behavior.
• Understanding of safe tool execution, approval workflows, and multi‑user data risks.
• Strong ownership across prototyping and production, with the ability to explain technical tradeoffs.
• Experience with LLM agents, tool use, evaluation, and prompt engineering.

Salary range: $0 to $200,000 USD annually. Founding equity is available; percentage and vesting details are to be determined.

Location

On-site in San Francisco, United States. Candidates should be based in the Bay Area or willing to relocate.