AI ENGINEER

Westfield is hiring an AI Engineer to build AI use cases of different shapes and sizes that impact our core insurance workflows. You’ll work with other AI Engineers, software developers, and business stakeholders to ship features and assets that range in complexity from simple prompt workflows and document understanding to AI agents, RAG, computer use, and more. You’ll be involved in business use cases from design and architecture into implementation, testing, deployment, monitoring, and maintenance. Responsibilities: Build containerized AI services in Python. Implement clean APIs where needed and standards-based integrations for enterprise systems. Design retrieval & agent flows using industry-standard frameworks; implement prompt/tool versioning and safe rollouts (e.g., feature flags, canary). Guardrails & governance: help implement controls around PII handling, audit logging, RBAC, prompt-injection defenses, and egress controls. Evaluation automation: create eval harnesses, golden sets, regression gates, and basic business KPIs (e.g., quality, safety, latency, cost). Observability: instrument tracing/metrics/logging with standard tooling, integrate with enterprise monitoring/logging platforms, and build actionable dashboards/alerts. Operational rigor: contribute to runbooks and incident hygiene. Participate in the on-call rotation for the AI services you help own. CI/CD: use pipeline-as-code for delivery and keep code-quality/security gates clean for frequent deployments. Team play: embed with asset teams when appropriate. Contribute back reusable components, SDKs, and docs to the AI engineering platform. Job Qualifications: At least 2 years of software engineering experience, including at least 1 production-deployed GenAI use case for real business users or consumers. Strong Python and microservice fundamentals (e.g., FastAPI or similar, type hints, tests such as pytest) with an emphasis on well-structured, readable code. Hands-on experience with any AI orchestration frameworks (e.g., LangChain, LangGraph, OpenAI Agents SDK, PydanticAI or similar). Containers/orchestration experience: solid containerization understanding and hands-on with deploy/scale/config/secret management (e.g., Docker, Kubernetes/OpenShift). Observability experience: metrics, logs, tracing (e.g., OTel) and using these signals to debug production outages and performance issues. CI/CD discipline (e.g., Azure DevOps YAML or similar), code-quality/security gates (e.g., SonarQube, Snyk), and dependency management basics. Governance understanding: audit logs, RBAC, data-privacy boundaries, and change control in business-critical environments. Experience deploying and supporting multiple custom GenAI use cases in production. Familiarity with MCP, A2A, or other AI integration standards. Experience with RAG and vector search. Experience with Python dependency/build management (e.g., uv) and familiarity with ASGI servers (e.g., uvicorn).