Chubb is a world leader in insurance. With operations in 54 countries, Chubb provides commercial and personal property and casualty insurance, personal accident and supplemental health insurance, reinsurance and life insurance to a diverse group of clients. The company is distinguished by its extensive product and service offerings, broad distribution capabilities, exceptional financial strength, underwriting excellence, superior claims handling expertise and local operations globally. We are a fast-moving team delivering AI scalability and governance solutions across Chubb's product portfolio. We build AI-native, move with purpose, and value engineers who bring both hard work and sound judgment to complex problems. We are looking for an AI Engineer who has shipped ML and LLM systems, built quality and observability tooling around them in production, and is ready to go deeper on that problem at scale. In this hands-on role, you will take end-to-end ownership of individual services within a larger AI platform, covering the architecture, data layer, business logic, and API surface without splitting responsibility across specialisms. You will develop iteratively alongside a small team, with short feedback loops and a high bar for what ships. Design and build production-grade LLM-powered services in Python and Go, integrating with cloud AI APIs such as Azure OpenAI or AWS Bedrock. Take end-to-end ownership of individual services: data model, business logic, and API surface across all layers. Build configuration-driven systems where runtime behaviour is governed by stored configuration rather than code changes. Contribute to containerised deployments using Docker and Kubernetes, following established CI/CD pipelines. Build and own evaluation harnesses: golden datasets, rubric-based scoring pipelines,



regression suites, and experiment comparison frameworks. Design recording and data layers that connect live LLM calls to offline quality measurement, making the prompt version, model, and configuration active at decision time fully reproducible. Surface observability signals in dashboards that are actionable for engineers and legible to non-technical stakeholders. Software engineering and design patterns Hold a high bar on type safety (Pydantic, typed TypeScript), comprehensive error handling, idempotency, and setting-agnostic configuration. Design multi-tenant systems with real access control: hierarchical entitlements and role models, per-user OAuth delegation (MSAL/PKCE), and rate and quota enforcement. Work with versioned content and configuration as inputs alongside prompts: what a model receives at runtime is often composed from multiple managed sources, not a single template. Manage context windows deliberately through chunking strategy, token optimisation, and retrieval design. Plan and track your own work against clear outcomes in agile sprints. Partner with product and senior engineers to translate requirements into working AI features. Communicate clearly across technical and non-technical audiences. 6-8 years building production software, with recent, substantial work on LLM-based systems that real users depend on. Deep experience with Python / Go / Rust and similar languages,



building safe, scalable, multi-tenant production systems. Experience with test-driven development as a design discipline, writing tests first rather than retrofitting them. Direct experience with at least one frontier provider SDK (Anthropic, OpenAI, Google) at the agent-loop level, not just chat completions. Fluency in software design patterns and the taste to know which problem each one actually solves. Solid command of LLM behaviour including prompt engineering, structured outputs, function calling, and context window management. Familiarity with REST APIs and cloud AI services including Azure OpenAI, AWS Bedrock, or GCP Vertex AI. Ability to work through ambiguity with stakeholders and turn a vague capability ask into a defensible technical design. Google ADK, Mastra (including declarative YAML workflows), Pydantic AI, Semantic Kernel, CrewAI, LlamaIndex, AutoGen — breadth here is useful, and having formed opinions about where each breaks down is more useful still. underwriting, claims, reinsurance) You design with standard software engineering patterns before you code. You give and take direct technical feedback well. Ownership of platform foundations used across a global organization, not a proof of concept that dies in a demo. Chubb Canada does not use artificial intelligence (AI) tools to assess, screen, or select applicants. It is our policy to provide equal employment opportunities to employees and applicants based on job-related qualifications and ability to perform a job. If a selected applicant requests accommodation during the recruitment process, Chubb will consult with the applicant in order to provide suitable accommodation that takes into account the

📌 Remote AI Engineer (Canada)
🏢 Chubb
📍 Canada