Staff Engineer, Agentic AI

About the Role This is a senior technical leadership role at the heart of an early-stage AI software company building intelligent agents for hardware engineers. You will own the core agent intelligence layer that turns engineers' intent into reliable, cost-efficient multi-step workflows across desktop CAD, simulation, and PLM tools. Reporting directly to the CTO, the work you do here determines the product's real-world value to enterprise customers. What You'll Do - Lead development of the agent intelligence layer that executes multi-step workflows across complex desktop engineering software. - Serve as technical lead for a small team of AI engineers, a user researcher, and domain expert contractors. - Own the full product loop: define agent capabilities from user stories, build implementations, and benchmark against real workflows. - Drive agent task success rate by defining evaluation frameworks, establishing baselines, and iterating on completion metrics. - Set and enforce per-task token budgets and track cost per completed workflow to ensure commercial viability. - Build rigorous, reproducible evaluation infrastructure grounded in validated user stories. - Lead user story mapping and validation through interviews and close collaboration with domain experts. - Translate validated user stories into testable evals, closing the loop between user research and benchmarking. - Own agent architecture decisions including tool-calling, state management, error recovery, model routing, and context management. - Act as a player-coach: write production code, review designs, unblock the team, and raise engineering standards. - Collaborate cross-functionally with integrations, product, and customers during POCs to align agent behavior with real-world usage. What We're Looking For - 7+ years of software engineering experience, including at least 2 years building LLM-based agents that take real-world actions. - Deep experience designing LLM application architectures: model selection, context and window management, retrieval, tool calling, and orchestration patterns. - Hands-on experience shipping AI or LLM tooling on top of proprietary engineering data or desktop engineering software (for example, agents or MCP servers over CAD, PLM, or simulation platforms); general-purpose chatbot or web-app RAG work alone does not qualify. - Strong Python proficiency and familiarity with LLM function calling, tool APIs, observability and tracing, and evaluation frameworks. - Proven ability to build evaluation and benchmarking frameworks measuring task completion, cost efficiency, and failure modes. - Technical leadership experience: setting direction for small teams of 3 to 6 engineers and performing meaningful code review while continuing to write production code. - Experience with desktop automation or programmatic control of applications such as COM or similar interfaces. - Domain background in mechanical engineering, CAD, CAE, PLM, or an adjacent engineering-software field. - Familiarity with enterprise deployment constraints on locked-down corporate workstations. - Track record contributing to public benchmarks, publications, or open-source agentic AI projects is a plus. Compensation & Benefits Base salary range: $160,000 to $250,000 USD annually , plus equity. Visa sponsorship is not available for this role. Location On-site in San Francisco, California, United States .