AI Engineer- Applied AI

Guidewire Software

1d

About The Position

Guidewire is hiring an AI Engineer to build, evaluate, and harden Concierge, its production omnichannel AI agent for property and casualty insurers. Concierge handles policyholder calls after accidents, gathers first notice of loss information, asks relevant questions, and creates claims in ClaimCenter. The role focuses on the agent’s orchestration, context, tools, and evaluation systems, with a gradual, evidence-based expansion of agent autonomy.

The position involves developing agent capabilities, measuring their quality, and using evaluation results and production evidence to guide improvements. Work includes synchronous voice, where latency is a product requirement, and regulated claims intake, where omissions or inaccuracies can affect claim costs. The engineer will collaborate with product and carrier stakeholders to shape what the agent should do, balancing rapid delivery with the accuracy required by claims workflows.

Guidewire is an equal opportunity and affirmative action employer committed to an inclusive workplace and providing individualized accommodations during the hiring process. All offers are contingent on applicable criminal history and other background checks.

Requirements

• Experience shipping an LLM application relied on by real users.
• Fluency in LLMs, context engineering, retrieval-augmented generation, and agentic workflows, with underlying machine learning and deep learning expertise.
• Ability to make unpredictable AI systems sufficiently reliable through disciplined evaluation, error analysis, and statistical measurement.
• Ability to reason about cost, latency, reliability, and scalability tradeoffs.
• Experience designing data stores and distributed systems, writing tests, and taking security and privacy seriously.
• Advocacy for CI/CD process automation.
• Experience working with coding agents, including managing context, deciding when specifications are useful, providing verifiers, and judging when to intervene.
• Product sense and sufficient insurance context to help shape the agent’s capabilities and make sound delivery-versus-accuracy decisions.
• Commitment to continuous learning and adapting working practices as tools change.

Nice To Haves

• Experience with real-time or streaming voice systems, including ASR, TTS, telephony, or SBC/SIPREC.
• Experience in insurance, claims, or another regulated domain where errors have consequences.
• Experience building internal evaluation or observability tools adopted by other engineers.
• Experience with machine learning principles, model experimentation, or training and deploying models in production.
• Experience in P&C insurance or exposure to Guidewire products and services.
• Experience applying prompt or pipeline optimization frameworks such as DSPy or GEPA to a production system.

Responsibilities

• Own end-to-end agent capabilities, including prompt and context architecture, retrieval over policy and coverage data, tools and API calls into core claims systems, and handoff to a human when appropriate.
• Build and operate the evaluation loop, including golden sets, trajectory evaluation, LLM-as-judge, production call-trace error analysis, and release gating.
• Improve containment and resolution rates while maintaining accuracy, and instrument the system to measure changes in those outcomes.
• Work on the voice path, including turn-taking, interruption handling, latency budgets, and the telephony layer such as LiveKit and SIP.
• Attend carrier calls and listen to call recordings to identify and address conversational problems.
• Help decide what the agent should do next, applying product judgment and insurance context to balance rapid MVP delivery with claims workflow accuracy.
• Keep learning and adapting as AI tools and practices evolve.

Benefits

• Health insurance
• Dental insurance
• 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, subject to various factors.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed