Principal AI Agent Engineer

Principal AI Agent Engineer

San Francisco and Boston

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 San Francisco (Berkeley), hybrid (2 days/week in office)

About the Role

As a Principal AI Agent Engineer, you define what "great" looks like for agent engineering at Liberate. You set the technical bar, shape how we deploy AI at scale, and ensure we build leverage instead of heroics.

You operate across customers, teams, and initiatives. You are trusted with the hardest problems, the messiest launches, and the highest-risk decisions. Your impact shows up not just in what you ship, but in how the organization gets stronger around you.

What You'll Do

• Act as the technical authority for agent architecture, quality, and deployment
• Own the most complex and high-risk customer launches and recoveries
• Define standards for agent design, prompts, evals, monitoring, and launch readiness
• Identify systemic gaps and drive solutions that reduce repeat incidents and toil
• Partner closely with Platform, Data Science, and Product to shape agent strategy
• Design reusable frameworks that turn customer work into durable platform leverage
• Lead by example in reviews, incidents, retros, and hard tradeoff decisions
• Mentor Staff and Senior engineers and raise the bar across the org

What We're Looking For

Must Have

• 10+ years of software engineering experience, including senior technical leadership
• Proven track record of owning large, ambiguous systems in production
• Deep understanding of system design, failure modes, and operational excellence
• Strong intuition for AI agent behavior, evaluation, and risk management
• Ability to set standards and influence without formal authority
• Calm, decisive leadership during incidents and crunch time
• High bar for quality, leverage, and long-term system health

Nice to Have

• Experience designing or scaling agentic or LLM-powered platforms
• Experience in regulated, high-stakes, or customer-facing systems
• Prior Staff/Principal/Distinguished-level experience at a strong engineering org