About the Role Join a small AI engineering team at an early-stage engineering software company building agentic AI for complex engineering workflows. As a hands-on technical leader, you will shape the agent intelligence that helps mechanical engineers complete multi-step tasks across desktop engineering tools, connecting user research, reliable task execution, and product delivery. What You'll Do • Lead the design and development of agent capabilities for multi-step workflows in desktop engineering software. • Define evaluation frameworks, build reproducible benchmarks from validated user stories, and improve task completion while tracking failure modes. • Set per-workflow token budgets and measure cost per completed task to support efficient, commercially viable systems. • Partner with user researchers and domain experts to document and validate engineering workflows, then translate them into test cases. • Prioritize workflow coverage based on customer value and technical feasibility. • Own agent architecture decisions across tool calling, state management, error recovery, model routing, and context management. • Provide technical direction to a small team, review designs and code, unblock teammates, and contribute production code. • Collaborate with product, integrations, and customers to align agent behavior with real-world needs. What We're Looking For • At least 7 years of software engineering experience, including 2 or more years building LLM-based agents that take real-world actions. • Deep experience with LLM application architecture, including model selection, context management, retrieval, tool calling, and orchestration. • Strong Python skills and familiarity with function calling, tool APIs, tracing or observability, and evaluation tools. • Experience building rigorous agent evaluation and benchmarking systems that measure task completion, cost efficiency, and failure modes. • Hands-on technical leadership experience setting direction and reviewing code for a small team while continuing to ship production software. • Experience applying AI or LLM tooling to proprietary engineering data or desktop engineering software. Background in mechanical engineering, CAD, CAE, PLM, or an adjacent domain is valuable. • Familiarity with desktop automation or programmatic application control, such as COM, and enterprise workstation constraints. Compensation & Benefits Annual salary range: $160,000 to $250,000 USD. Visa sponsorship is not available. Location On-site in San Francisco, California, United States.