Founding Harness Engineer
Core
Design and build the agent runtime and reliability systems for an AI coworker that acts safely and dependably in real work.
Role type
Founding engineer (AI agent runtime & reliability)
Builds
Agent runtime, system prompts, evaluation harnesses, and safe execution boundaries for an AI coworker product.
Domain
Artificial Intelligence / LLM Agents / System Reliability
Deliverable
production ML models
Required skills
LLM agent architecture, system prompt design, evaluation and regression testing, safe tool execution, multi-tenant data separation, reliability engineering
Preferred skills
Early-stage startup experience, product development with leadership
Technologies
LLMs, agent frameworks, testing frameworks
Responsibilities
Design agent runtime logic for context gathering, tool selection, and task completion; Write and refine system prompts; Build evaluation and regression tests for agent behavior; Implement safe execution boundaries and approval gates; Improve reliability for long-running tasks and retries; Collaborate with leadership and early users on product development.