AI Engineering Lead — Agentic Systems & Platform

Baker Tilly Advisory Group, LP; San Francisco (CA); On-site; USD 250,000 - 400,000; Full time

Job summary

Baker Tilly, a leading advisory firm, seeks a Head of AI Engineering in San Francisco to define how AI agents are designed, orchestrated, evaluated, and deployed. This role sets standards for task decomposition, memory management, tool use, and human-in-the-loop controls across product teams.

The leader will own the evaluation harness, baselines, and agent experiences end-to-end, mentor engineers, and collaborate with internal teams to advance Baker Tilly's agentic engineering capabilities.

Qualifications

• Bachelor's degree in computer science, engineering, or a related field, or equivalent practical experience.
• 15+ years of software engineering experience, including 3+ years building and deploying LLM-based or agentic systems in production.
• Staff- or principal-level engineering experience with designed production agent systems.
• Strong knowledge of agentic tech stack including orchestration, tool calling, retrieval with vector/graph approaches, and memory management.

Responsibilities

• Define and build agentic reference patterns including task decomposition, orchestration, context engineering, memory management, tool use, and failure recovery.
• Maintain the agent pattern library and establish orchestration standards for product teams.
• Own the Compass agents and full-stack experiences end to end on the intelligence layer.
• Build and own evaluation harness, baselines, and regression discipline for agents.

Skills

Python

TypeScript

LLM-based systems

Agentic engineering

Code reviews

Collaboration

Observability

Production-grade code

Education

Bachelor's degree or higher

Advanced degree preferred

Tools

Vector databases

Graph databases

APIs

Job description

Baker Tilly, a leading advisory firm, seeks a Head of AI Engineering in San Francisco to define how AI agents are designed, orchestrated, evaluated, and deployed. This role sets standards for task decomposition, memory management, tool use, and human-in-the-loop controls across product teams.

The leader will own the evaluation harness, baselines, and agent experiences end-to-end, mentor engineers, and collaborate with internal teams to advance Baker Tilly's agentic engineering capabilities.