Founding Harness Engineer
Core
Design and build the runtime and safeguards for AI agents to take initiative, work reliably, and handle tasks safely.
Role type
Founding engineer (AI agent runtime & safety)
Builds
AI agent runtime, system prompts, evaluation harnesses, safety boundaries
Domain
Artificial Intelligence / LLM Agents
Deliverable
production ML models
Required skills
LLM agent development, tool-using agents, system prompt design, evaluation & regression testing, safety boundaries implementation, multi-tenant data separation
Preferred skills
Early-stage startup experience, prototyping to production ownership, technical tradeoff analysis
Technologies
LLMs, agent frameworks, testing frameworks
Responsibilities
Design agent runtime for context gathering, action decision, tool selection, and approval; Write and refine system prompts; Build evaluation and regression tests for agent behavior; Implement safety gates and data separation; Collaborate with founding team and early users
Seniority
Founding, hands-on IC
