Director of Engineering, AI Agent Engineering, Forward Deployed

About Us:

Liberate builds AI agents to automate manual tasks for the $2.7T insurance industry. We started with voice — the hardest and most valuable channel in insurance — and are now expanding into full workflow automation across sales, servicing, and claims. Our long-term vision is to build reasoning agents capable of handling the entire spectrum of insurance carrier and broker operations. We've raised $72M to date, including a $50M Series B in October 2025, backed by top-tier venture firms.

Location: Boston or Bay Area, hybrid preferred (2x/week in office)

Reporting: VP Engineering, dotted line partnership with CPO, and Customer Success leadership

Mission
Build and scale Liberate’s forward deployed agent engineering function. Turn complex customer workflows into production grade agent deployments quickly, safely, and repeatably, while feeding product and platform improvements upstream.

What you will do

• Lead multiple forward deployed pods delivering customer facing agent workflows end to end.
• Build the operating system, intake and scoping, technical discovery, success metrics, deployment gating, and post launch validation.
• Define and enforce engineering quality bars for agent systems, eval coverage, reliability, and observability.
• Partner with Product to translate repeated customer patterns into roadmap priorities and platform primitives.
• Own planning cadence, monthly lookahead and quarterly execution, capacity, dependencies, and predictable delivery.
• Coach pod leads and senior engineers, hire and develop managers as needed.
• Stay hands on where it matters, debug hard issues, review designs, set the technical bar.

What we are looking for

• 10+ years in software engineering, 5+ in engineering leadership, ideally scaling customer facing or forward deployed teams.
• Strong systems instincts, distributed systems, APIs, reliability, production debugging.
• Comfort with AI agent systems, orchestration, evals, tool calling, safety patterns, and rapid iteration.
• Customer facing leadership presence, you can translate ambiguity into a plan and deliver.

Success looks like

• Faster time to production for new deployments, fewer surprises, higher reuse of patterns.
• Clear signal into platform, fewer one off builds, more leverage over time.
• Predictable delivery across pods with a consistent quality bar.
  
  

What you own

• Own outcomes for forward deployed agent delivery across multiple customers or verticals, reliability, eval quality, timeline predictability.
• Build the playbook, intake, scoping, deployment methodology, rollout gates, post launch learning loop.
• Set quality bars for agent systems, evals, safety patterns, observability, incident learnings, and what goes upstream into the platform.
• Staff and grow pod leads, coach senior ICs into leads, keep execution tight when teams are fluid.