AI Engineer

Overview

Guidewire is seeking an AI Engineer for its Professional Services AI Engineering team in Bangalore. You will work as the AI-side member of a Strike Team, pairing with a Product Engineer to deliver AI productization projects end-to-end, with a primary focus on harness engineering and prompt engineering.

What you'll do

• Build and maintain LLM harnesses that power each AI feature, including agent loops, tool/function calling, context construction, memory, retries, and failure handling.
• Use frameworks like LangChain, LlamaIndex, or LangGraph where they fit, and write custom orchestration where they don't.
• Design, iterate, and version prompts as first-class assets, run structured prompt experiments, measure deltas with eval datasets, and keep prompt libraries clean and reviewable.
• Build and operate RAG pipelines that extract information from documents and parse it into structured knowledge bases, including chunking, indexing, retrieval, reranking, prompt assembly, and response handling.
• Collaborate with the AI Architect to shape and refine RAG patterns.
• Generate embeddings and manage vector indexes (e.g., OpenSearch, Pinecone, pgvector), tuning them for retrieval quality and cost.
• Build extraction and parsing pipelines for documents, structured records, and customer datasets so they are clean, labeled, and ready for downstream AI work.
• Write and operate accuracy validation scripts, maintain evaluation datasets, and report quality metrics to the Strike Team and the AI Architect.
• Apply traditional ML where appropriate, such as classification, clustering, and lightweight fine-tuning, to complement LLM-based components.
• Perform data analysis that informs AI design decisions, including sample inspection, error analysis, and prompt iteration.

What you'll need

• Bachelor's or Master's degree in Computer Science, Data Science, Statistics, or a related technical field.
• 3+ years of AI or data science experience, with hands-on time in LLM-based application development.
• Strong Python skills, including the standard data science stack (pandas, numpy, scikit-learn).
• Hands-on experience building LLM harnesses (agent loops, tool/function calling, structured outputs) against APIs such as Anthropic, OpenAI, or Bedrock.
• Strong prompt engineering practice: structured iteration, prompt versioning, and prompt evaluation against datasets.
• Working experience with at least one orchestration framework (LangChain, LlamaIndex, LangGraph) and at least one vector database.
• Comfortable with embeddings, similarity search, and basic retrieval evaluation.
• Working knowledge of classical ML for analysis and lightweight modeling tasks.
• Comfort using AI coding assistants (Claude Code) for daily work.
• Able to write clean, tested code that ships to production, not just notebooks. Familiar with Git, code review, and basic CI/CD.
• Strong instinct for data analysis, error inspection, and iterative experimentation.

Nice to have

• Hands-on experience with agentic frameworks (LangGraph, Claude Agent SDK, OpenAI Agents) or custom agent harnesses in production.
• Experience building structured eval harnesses (golden sets, regression suites, LLM-as-judge patterns).
• Hands-on AWS experience (Bedrock, SageMaker, OpenSearch).
• Any experience with model fine-tuning or distillation.
• Familiarity with Guidewire products or the insurance domain.
• Prior experience working on document-heavy, regulated, or insurance/finance datasets.

Details

• Location: Bangalore, India.