AI Engineer- Applied AI

United States - Remote

Product Strategy/Full time/Remote

About the Product

Concierge is Guidewire's omnichannel AI agent for P&C carriers. It answers the phone when a policyholder has just had an accident, takes first notice of loss, asks the questions a good adjuster would ask, and writes a clean claim into ClaimCenter. It runs in production today with real carriers and real policyholders, not as a demo.

Two things make this harder than a typical chatbot. First, it has synchronous voice: latency is a product requirement, not a metric on a dashboard. Second, FNOL is a regulated event where the quality of the intake determines the eventual cost of the claim. A missed question early is a bigger loss reserve later.

The Role

You will build, evaluate, and harden the agent itself: the orchestration, the context it sees, the tools it can call, and the evals that tell us whether a change made it better or just different.

Our rollout philosophy is a dimmer, not a light switch. We widen the agent's autonomy one notch at a time, and every notch has to be earned with evidence. Much of your work is producing that evidence, then acting on what it says.

Job Description

### What you'll do

• Own end-to-end slices of the agent: prompt and context architecture, retrieval over policy and coverage data, tool and API calls into core claims systems, and handoff to a human when the agent should stop.
• Build and run the eval loop, golden sets, trajectory evaluation, LLM-as-judge, error analysis on real production call traces, and make it the thing that gates releases.
• Drive containment and resolution rates up without trading away accuracy, and instrument the system well enough that we can tell which of the two moved.
• Work directly on the voice path: turn-taking, interruption, latency budgets, and the telephony layer underneath (LiveKit, SIP).
• Sit in on carrier calls and listen to recordings. The best fixes usually come fr