Senior Technical Leader — Agentic AI (Engineering Tools)

Fruition Executive Search•San Francisco, CA

3d•$160,000 - $240,000•Onsite

About The Position

The Senior Technical Leader — Agentic AI will own the core agent intelligence that turns mechanical engineers’ intent into reliable, cost-efficient, multi-step workflows across desktop engineering tools. The role combines applied agentic AI, user research, and product delivery, and is responsible for determining the product’s real-world value to enterprise customers. The position leads development of the agent intelligence layer and serves as technical lead for a small team of AI engineers, a user researcher, and domain expert contractors. Reporting to the CTO, the leader owns the product loop from defining agent capabilities based on user stories through implementation and benchmarking against real workflows. The role also owns agent architecture decisions, evaluation infrastructure, task success and cost metrics, and close collaboration with integrations, product, and customers during proofs of concept. This is a full-time, on-site role in San Francisco. Sponsorship and relocation are not available.

Requirements

At least 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, including model selection, context/window management, retrieval, and orchestration patterns.
Proven ability to build evaluation and benchmarking frameworks that measure task completion, cost efficiency, and failure modes.
Technical leadership experience setting direction for small teams of 3–6 engineers and performing meaningful code review.
Strong Python skills and familiarity with LLM tooling, including function calling, tool APIs, observability/tracing, and evaluation frameworks.
Experience with desktop automation or programmatic control of applications, such as COM or similar.
Domain experience in mechanical engineering, CAD/CAE, PLM, or adjacent industries.
Understanding of enterprise deployment constraints on locked-down corporate workstations.

Nice To Haves

Track record contributing to public benchmarks, publications, or open-source agentic AI projects.

Responsibilities

Lead development of the core 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.
Improve agent task success rates by defining evaluation frameworks, establishing baselines, and iterating on completion metrics.
Set and enforce per-task token budgets and track cost per completed workflow.
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 evaluations and connect research to benchmarking.
Own agent architecture decisions, including tool-calling, state management, error recovery, model routing, and context management.
Write production code, review designs, unblock the team, and raise engineering standards.
Collaborate with integrations, product, and customers during proofs of concept.