Staff Engineer - Agentic AI

About the role

A well‑funded early‑stage AI startup in the mechanical engineering software space is seeking a Staff Engineer to own the core agent intelligence layer that turns engineers' intent into reliable, cost‑efficient multi‑step workflows across complex desktop tools. This senior technical leadership role reports directly to the CTO and sits at the intersection of applied agentic AI, user research, and product delivery.

Key responsibilities

• Lead development of the core agent intelligence layer executing multi‑step workflows across complex desktop engineering software (CAD, CAE, PLM).
• 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.
• Define and maintain an evaluation framework, establish baselines, and systematically improve task success rates and cost efficiency.
• 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 direct interviews with domain experts.
• Make architecture decisions on tool‑calling strategies, 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.

Required profile

• 7+ years of software engineering experience, including at least 2 years building agentic LLM‑based agents that act in the real world.
• Deep experience designing LLM application architectures (model selection, context/window management, retrieval strategies, tool‑calling frameworks, orchestration patterns).
• Strong evaluation and benchmarking instincts for agentic systems; familiarity with SWE‑bench, GAIA, or τ‑bench.
• Proven track record shipping AI systems with measurable outcomes (task success rate, cost efficiency).
• Strong Python skills and hands‑on experience with LLM tooling, function calling, tool‑use APIs, and observability tools such as Logfire or LangSmith.
• Experience leading a small technical team (3–6 engineers) and driving architecture decisions.

Required skills

• Python
• LLM tooling (function calling, tool‑use APIs)
• Logfire or LangSmith observability tools
• Evaluation frameworks for agentic AI
• Desktop automation and COM
• CAD, CAE, PLM domain knowledge

What we offer

• Salary range $160,000 – $250,000 USD annually, based on experience.
• Equity participation in an early‑stage Series A company.