[Hiring] Junior AI Engineer @Guidewire Software

Role Description

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:

• It has synchronous voice: latency is a product requirement, not a metric on a dashboard.
• 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:

• 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.
• 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 from hearing where the conversation went sideways, not from reading the logs.

Qualifications

• Building and deploying AI applications. You've shipped an LLM application that real users depend on, and you know that the hard part is that the output is not predictable.
• Fluent in the building blocks LLMs, context engineering, RAG, agentic workflows, and have real ML and deep learning depth underneath that fluency.
• Know how to make an unpredictable system behave predictably enough to trust: disciplined evals, error analysis, and statistical measurement.
• Software engineering fundamentals. You can reason about cost, latency, reliability, and scalability as tradeoffs rather than goals.
• Designed data stores and distributed systems, write tests, and take security and privacy seriously while advocating CI/CD process automation.
• Using coding agents. You work with coding agents daily and you're good at it: managing their context, deciding when a spec is worth writing and when it isn't.
• Shaping the build. You'll be in the room where we decide what the agent should do next, which means you need product sense and enough insurance context to argue about it.
• Keep learning. This field looks different every six months and we expect to keep changing our minds.

Requirements

• Real-time or streaming voice systems (ASR, TTS, telephony, SBC/SIPREC).
• Insurance, claims, or another regulated domain where being wrong has a cost attached.
• Experience building internal eval or observability tooling other engineers actually adopted.
• Experience in Machine learning principles, or have experience in model experimentations, training and deploying models in Productions.
• Experience in P&C Insurance or exposure to Guidewire products and services.
• Prompt or pipeline optimization frameworks (DSPy, GEPA) applied to a production system.

Benefits

• Health, dental, and vision insurance.
• Paid time off.
• Company sponsored retirement plan.
• Some roles may be eligible for the annual company bonus plan, commissions, and/or long term incentive awards.

Company Description

Guidewire is the platform P&C insurers trust to engage, innovate, and grow efficiently. We combine digital, core, analytics, and AI to deliver our platform as a cloud service. More than 540+ insurers in 40 countries, from new ventures to the largest and most complex in the world, run on Guidewire.

As a partner to our customers, we continually evolve to enable their success. We are proud of our unparalleled implementation track record with 1600+ successful projects, supported by the largest R&D team and partner ecosystem in the industry.

For more information, please visit www.guidewire.com and follow us on Twitter: @Guidewire_PandC.