Senior Software Engineer

Summary

Our Product Strategy organization is shaping the next generation of Guidewire's cloud, data, and AI-powered platform for P&C insurers worldwide. We partner closely with Product Development & Operations to deliver secure, scalable solutions that improve reliability, performance, and customer value. You'll join a collaborative, inclusive team that experiments, learns by doing, and works across Python, Type Script/React, and modern AWS-native services. In this Senior Software Engineer role, you'll be the engineering front line for complex customer scenarios - triaging production issues, engineering hotfixes, and building the tools that keep our platform reliable 'll apply deep SaaS backend expertise across Python, LLM and AI exposure to improve observability, streamline customer implementations, and unlock the full value of our AI-infused product strategy.

This is an opportunity to contribute directly to Guidewire's mission to transform how the world's P&C insurers do business through cloud, analytics, and AI, while shaping how our platform runs in real customer environments every day.

• Document Ingestion & Pipelines:
  Design and maintain scalable data processing pipelines for ingesting, parsing, cleaning, and indexing multi-format unstructured and semi-structured documents from varied knowledge sources.
• Knowledge & Retrieval Systems:
  Architect and optimize Retrieval-Augmented Generation (RAG) pipelines, semantic and hybrid search workflows, and context-assembly engines to deliver accurate, high-relevance information to downstream application models.
• Metadata & Knowledge Organization:
  Implement robust schemas for document versioning, chunking strategies, metadata enrichment, taxonomy management, and granular permission-aware context filtering.
• Back-End API & Service Development:
  Build reliable, high-throughput RESTful and streaming APIs in Python to expose context and knowledge services seamlessly to internal and external applications.
• Performance & System Efficiency:
  Optimize background processing, memory overhead, database indexing, caching strategies, and queue-based batch operations to minimize latency and manage operational compute costs.
• Evaluation & System Observability:
  Implement monitoring, logging, and continuous evaluation frameworks to track context retrieval precision, indexing health, API performance, and data drift in production.
• Clean Architecture & Scalable Design:
  Maintain clean abstraction layers across data stores, embedding services, and language models to keep core domain logic modular, decoupled, and vendor-agnostic.

• 6+ years of experience designing, building, and maintaining production back-end microservices and data pipelines using Python.
• Hands-on experience with document parsing, text chunking, metadata enrichment, and building scalable pipelines for unstructured knowledge processing.
• Solid understanding of modern retrieval paradigms, including semantic search, vector indexing, lexical/keyword search, hybrid search, and RAG architectures.
• Deep familiarity with modern Python back-end practices, asynchronous programming (async/await), relational/non-relational database design, and background job processing systems.
• Proven experience building clean RESTful/streaming APIs, applying object-oriented/functional design patterns, and maintaining vendor-neutral software abstractions.
• Experience with cloud environments, containerized deployments (e.g., Docker, Kubernetes), message queues, caching layers, and CI/CD pipelines.
• Strong commitment to testing, technical documentation, code reviews, and clear cross-functional collaboration with product, data, and front-end engineering teams.

The Canadian CAD base salary range for this…