5 hours ago
Base Salary
$160k - $250k/yr
Responsibilities
- Lead development of the agent intelligence layer for 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 product loop from user-story definition through implementation, benchmarking, and iteration.
- Define evaluation frameworks, baselines, completion metrics, token budgets, and cost tracking for agent workflows.
- Build reproducible evaluation infrastructure grounded in validated user stories.
- Lead user interviews, story mapping, domain-expert collaboration, and translation of user stories into testable evaluations.
- Own architecture decisions involving tool calling, state management, error recovery, model routing, and context management.
- Write production code, review designs, unblock the team, and raise engineering standards as a player-coach.
- Collaborate with integrations, product, and customers during proof-of-concept engagements.
Requirements
- 7+ years of software engineering experience, including at least 2 years building LLM-based agents that take real-world actions.
- Exceptional technical depth in complex agentic systems and strong hands-on individual-contributor capability.
- Deep experience with LLM application architecture, including model selection, context management, retrieval, tool calling, and orchestration.
- Experience building evaluation and benchmarking frameworks for agent task completion, cost efficiency, and failure modes.
- Strong Python proficiency and familiarity with LLM function calling, tool APIs, observability/tracing, and evaluation tooling.
- Experience setting technical direction and reviewing code for a small engineering team while continuing to write production code.
- Experience shipping AI or LLM tooling over proprietary engineering data or desktop engineering software, such as CAD/PLM APIs, MCP servers over BOM and revision data, or RAG over firmware, schematics, or manufacturing telemetry.
- Experience with desktop automation or programmatic application control, such as COM or similar technologies.
- Understanding of enterprise deployment constraints on locked-down corporate workstations.
- Background in mechanical engineering, CAD/CAE, PLM, or an adjacent engineering-software domain is a strong plus.
- Contributions to public benchmarks, publications, or open-source agentic AI projects are a plus.
Benefits
- Base salary plus equity.
- On-site work in San Francisco, California.
- Visa sponsorship is not available for this role.