Staff Engineer — Agentic AI

ABOUT THE ROLE A well-funded, early-stage B2B SaaS company building AI agent infrastructure for mechanical engineering workflows is hiring a Staff Engineer — Agentic AI to own the core agent intelligence layer. This is a high-impact, senior technical leadership role reporting directly to the CTO. You'll sit at the intersection of applied agentic AI, user research, and product delivery — determining real-world value for Fortune 100 enterprise customers in the CAD, CAE, and PLM space. You'll lead a small team of AI engineers, a user researcher, and domain expert contractors, acting as a player-coach who writes production code and sets technical direction. WHAT YOU'LL DO - Lead development of the core agent intelligence layer that executes multi-step workflows across complex desktop engineering software. - Own the full product loop: define agent capabilities from user stories, build implementations, and benchmark against real workflows. - Drive agent task success rate — define the evaluation framework, establish baselines, and systematically improve completion metrics. - Set and enforce per-task token budgets; track cost per completed workflow to ensure commercial viability. - Build rigorous, reproducible evaluation infrastructure grounded in validated user stories (SWE-bench-level rigor applied to engineering workflows). - Lead user story mapping and validation through interviews and close collaboration with domain experts. - Translate validated user stories into testable evals and close the loop between research and benchmarking. - Own agent architecture decisions: tool-calling strategies, state management, error recovery, model routing, and context management. - Set technical direction, review architecture decisions, unblock the team, and raise the engineering bar across a team of 3–6 engineers. - Collaborate cross-functionally with integrations, product, and customers during POCs to align agent behavior with real-world usage. WHAT WE'RE LOOKING FOR Must-haves: - 7+ years in software engineering, including at least 2 years building agentic LLM-based systems that act in the real world (multi-step workflows, tool-calling, failure handling, cost constraints). - Deep experience with LLM application architecture: model selection, context/window management, retrieval strategies, tool-calling frameworks, and orchestration patterns. - Strong evaluation and benchmarking instincts for agentic systems — task completion, cost efficiency, and failure mode analysis; familiarity with SWE-bench, GAIA, or τ-bench. - Proven track record of shipping AI systems with measurable outcomes, not just demos. - Proficiency in Python and the LLM tooling ecosystem (function calling, tool use APIs, tracing/observability tools such as Logfire or LangSmith, evaluation frameworks). - Experience leading a small technical team (3–6 engineers): setting direction, performing code reviews, and driving architecture decisions. Nice-to-haves: - Experience with desktop automation, COM, or programmatic control of applications (beyond web APIs). - Background in mechanical engineering, CAD/CAE, PLM, or adjacent industries. - Familiarity with enterprise deployment constraints on locked-down corporate workstations. - Published work or open-source contributions in agentic AI systems. - Experience building or contributing to public benchmarks for AI agents. Note: Visa sponsorship is not available for this role. COMPENSATION & BENEFITS - Salary: $160,000 – $250,000 USD annually - Early-stage equity - Direct line to executive leadership and outsized scope of impact LOCATION This is an on-site role based in San Francisco, CA. Candidates must be willing to work from the office.