AI Architect
Guidewire SoftwareResponsibilities
- Create reusable technical blueprints for AI features, including architecture, data requirements, model strategy, evaluation, and delivery risks.
- Define model-selection patterns for LLMs, classical NLP/NLU, rules-based approaches, and lightweight ML.
- Design reusable harness patterns for agent loops, tool and function calling, context construction, memory, structured outputs, retries, and failure handling.
- Establish standards for prompt design, versioning, experimentation, evaluation, and regression testing.
- Design evaluation frameworks using golden datasets, regression suites, error analysis, LLM-as-judge patterns, and human review loops.
- Guide RAG and knowledge patterns including document parsing, chunking, embeddings, retrieval, reranking, prompt assembly, and grounded responses.
- Mentor P2/P3 AI engineers, review technical designs, create examples, and enable engineers to communicate architecture findings.
- Collaborate with Product, AI CoE, Professional Services, customer teams, and SI partners.
Requirements
- Bachelor's or master's degree in Computer Science, Data Science, Statistics, Machine Learning, Engineering, or a related technical field.
- 8+ years of experience in AI, machine learning, data science, software engineering, or solution architecture.
- Strong ability to translate ambiguous product or delivery goals into practical AI system designs.
- Deep understanding of LLMs, prompts, embeddings, retrieval, structured outputs, tool use, agentic workflows, and model failure modes.
- Ability to determine when classical NLP/NLU, rules-based approaches, lightweight ML, or structured extraction are preferable to generative AI.
- Strong Python or Java skills and ability to review and contribute to production-quality code.
- Experience designing LLM harnesses with orchestration, tool and function calling, context construction, retries, and fallback behavior.
- Experience with prompt engineering, versioning, evaluation, and regression testing.
- Working knowledge of RAG patterns, embeddings, retrieval evaluation, and vector search concepts.
- Familiarity with Git, code review, testing, CI/CD 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.
- Preferred experience with production agentic AI systems, structured evaluation harnesses, LLM-as-judge patterns, AWS AI and data services, model fine-tuning, distillation, domain adaptation, Guidewire or insurance, and regulated or document-heavy datasets.
Categories
About Guidewire Software
Guidewire is the platform P&C insurers trust to engage, innovate, and grow efficiently. More than 570 insurers in 43 countries, from new ventures to the largest and most complex in the world, rely on Guidewire products. With core systems leveraging data and analytics, digital, and artificial intelligence, Guidewire defines cloud platform excellence for P&C insurers. We are proud of our unparalleled implementation record, with 1,700+ successful projects supported by the industry’s largest R&D team and SI partner ecosystem. Our marketplace represents the largest partner community in P&C, where customers can access hundreds of applications to accelerate integration, localization, and innovation. For more information, please visit https://www.guidewire.com/.