Staff Engineer - Agentic AI
$160,000–$250,000 year
On-site · San Francisco, California, United States
Job Summary
Staff Engineer — Agentic AI is a senior technical leadership role responsible for owning the core agent intelligence layer that translates engineers' intent into reliable, cost-efficient multi-step workflows across desktop engineering tools. You will lead a small team of AI engineers, a user researcher, and domain expert contractors, report to the CTO, and drive architectural decisions, benchmarking, and production-grade delivery of agent capabilities in CAD/CAE/PLM environments. The role emphasizes setting evaluation frameworks, per-task budgets, and cost-conscious scalability, while collaborating cross-functionally with integrations, product, and customers during POCs to ensure agent behavior aligns with real-world usage. The position requires deep experience in LLM-based architectures, tool-calling, and enterprise-grade AI systems, plus hands-on Python development and leadership of a technical team; on-site in San Francisco, CA.
Required Qualifications
- 7+ years in software engineering
- 2+ years building agentic LLM-based agents with real-world use (tool-calling, multi-step workflows, failure handling, cost constraints)
- Deep experience designing LLM application architectures: 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, failure mode analysis; familiarity with SWE-bench, GAIA, or τ-bench
- Proven track record shipping AI systems with measurable outcomes (e.g., agent task success rate, cost efficiency)
- Strong Python skills and hands-on experience with LLM tooling (function calling, tool use APIs, tracing/observability tools such as Logfire or LangSmith, evaluation frameworks)
- Experience leading a small technical team (3–6 engineers)
- Strongly preferred: Experience with desktop automation, COM, or programmatic control of applications; background in mechanical engineering, CAD/CAE, PLM; familiarity with enterprise deployment constraints; published work or open-source contributions in agentic AI; experience building or contributing to public benchmarks for AI agents
Additional Requirements
- Visa sponsorship not available
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.