G

Guidewire

Cloud-based SaaS platform for P&C insurers

AI Architect

Natural Language Processing & LLMsConfirmed live in the last 24 hours
Full-timeBengaluru, Karnataka, IndiaNo salary listedIn-person

About the Job

Requirements

  • Bachelor's or Master's degree in Computer Science, Data Science, Statistics, Machine Learning, Engineering, or a related technical field.
  • Eight or more years of experience in AI, machine learning, data science, software engineering, or solution architecture.
  • Ability to translate ambiguous product or delivery goals into practical AI system designs.
  • Deep understanding of large language models, prompts, embeddings, retrieval, structured outputs, tool use, agentic workflows, and model failure modes.
  • Ability to recognize when classical natural language processing/natural language understanding, rules-based approaches, lightweight machine learning, or structured extraction are preferable to generative AI.
  • Strong Python and Java skills, including ability to read, review, and contribute to production-quality code.
  • Experience designing large language model harnesses, including orchestration, tool/function calling, context construction, retries, and fallback behavior.
  • Strong prompt engineering practice, including structured iteration, versioning, evaluation, and regression testing.
  • Working knowledge of retrieval-augmented generation patterns, embeddings, retrieval evaluation, and vector search concepts.
  • Comfort designing evaluation approaches using golden sets, regression suites, error taxonomies, and human review loops.
  • Familiarity with Git, code review, testing, continuous integration/continuous delivery concepts, cloud-based delivery, and production engineering practices.
  • Ability to explain complex AI trade-offs clearly and coach less experienced engineers without direct reporting authority.

Responsibilities

  • Create technical blueprints for AI features, including architecture, data needs, model strategy, evaluation approach, and delivery risks.
  • Define patterns for selecting which large language model to use for each call and when to use natural language processing/natural language understanding instead.
  • Shape reusable patterns for agent loops, tool/function calling, context construction, memory, structured outputs, retries, and failure handling.
  • Set standards for prompt design, versioning, review, experimentation, and regression testing as first-class engineering assets.
  • Design evaluation frameworks, golden datasets, regression suites, error analysis, and large-language-model-as-judge patterns to measure quality and guide decisions.
  • Guide document parsing, chunking, embeddings, retrieval, reranking, prompt assembly, and grounded response patterns.
  • Coach P2/P3 AI engineers, review technical designs, create examples, and help junior engineers present architecture findings clearly.
  • Partner with Product, AI CoE, PS, customer teams, and SI partners.
  • Help teams choose among agentic workflows, direct large language model calls, retrieval-augmented generation, classical natural language processing/natural language understanding, lightweight machine learning, or model fine-tuning.
  • Mentor P2/P3 AI engineers, review designs, create reusable patterns, and help the broader team explain AI design choices across Guidewire, SI partners, and customers.

Desired Qualifications

  • Experience with agentic frameworks or custom agent harnesses in production.
  • Experience building structured evaluation harnesses, regression suites, large-language-model-as-judge patterns, or production feedback loops.
  • Hands-on AWS experience with services such as Bedrock, SageMaker, OpenSearch, or related cloud-native AI/data services.
  • Experience evaluating or implementing model fine-tuning, distillation, or domain adaptation.
  • Familiarity with Guidewire products or the insurance domain.
  • Prior experience working on document-heavy, regulated, insurance, finance, or professional services datasets.

About the Company

Guidewire

Cloud-based SaaS platform for P&C insurers

Guidewire provides software for the property and casualty (P&C) insurance industry. Its platform is a cloud-based suite that helps insurers run core operations such as underwriting, policy administration, billing, and claims, with added analytics and AI features. Customers subscribe to the software as a service (SaaS) and pay for cloud access, implementation, and ongoing support. The company differentiates itself by its deep specialization in P&C, a large number of successful implementations (about 1,600), a track record of industry recognition (awards and a strong position in Gartner’s Magic Quadrant for P&C Core Platforms in North America), and an integrated set of digital, core, analytics, and AI tools designed to modernize insurers’ core systems. Its goal is to help P&C insurers modernize their technology, improve customer experiences, and grow their businesses through a cloud-based platform.

Company size
1,001-5,000
Company stage
IPO
Headquarters
San Mateo, CA
Founded
2001

Recently Posted Jobs

Explore more opportunities at Guidewire

See more jobs