Integrate with internal systems and external partners through governed APIs, event streams, and webhooks, with schema versioning
Build durable workflows and agentic AI features using tools like Temporal, Camunda, Step Functions, LangGraph, AutoGen, CrewAI, or the Claude Agent SDK, including human-in-the-loop steps, tool calling, MCP, and guardrails
Evaluate and monitor AI features with prompt versioning, evaluation sets, tool-call accuracy, task success, cost, latency, and human review gates
Build RAG, memory, ontology, and document capabilities, including ingestion, chunking, embeddings, vector and hybrid search, reranking, retrieval evaluation, and structured knowledge extraction
Protect retrieval and AI inputs with document access control, PII/PCI redaction, and defenses against prompt injection, while following security, privacy, and regulatory requirements
Build and maintain CI/CD pipelines, manage branching and release practices, review code thoroughly, keep pipelines healthy, resolve root causes, mentor engineers, and improve cloud-native automation where it helps
8+ years of software engineering experience, including 3+ years building distributed, data-intensive or platform systems in production; knowledge of and/or experience with insurance processes, regulatory requirements and industry standards is a plus
Bachelor's or Master's degree in Computer Science, Engineering or a related field (or equivalent experience)
Strong programming in Python, Java, Scala or similar, and strong SQL, with experience of microservices, APIs and event-driven architecture on AWS, Azure or GCP; experience with Kubernetes, Docker, Terraform, and/or GitOps is a plus
Solid distributed systems fundamentals: idempotency, retries and backoff, circuit breakers, consistency, structured logging, distributed tracing and correlation IDs; experience with Temporal, Camunda, AWS Step Functions, and/or Cadence is a plus
Experience with streaming (Kafka, Kinesis or Event Hubs) and distributed data processing (Spark, Flink or Beam), and with data modelling for SQL and NoSQL stores; experience with Delta Lake, Iceberg, and data governance and/or metadata management is a plus
Hands-on experience with LLM-based applications including at least one production or serious prototype using RAG (chunking, embeddings, vector search) or agents with tool calling; experience with LangGraph, AutoGen, CrewAI, Claude Agent SDK, MCP, and LLM evaluation and/or observability tools is a plus
Working knowledge of ontologies or knowledge graphs, and of data science and ML basics (Python data stack, model evaluation, how models are deployed and monitored); experience with Neo4j, MongoDB, GraphDB, JSON-LD, SHACL, Cypher, SPARQL, and/or Gremlin is a plus
Hands-on CI/CD experience building and maintaining Jenkins pipelines (Jenkins file, shared libraries) with automated test, scan and release stages, and Git workflows with pull requests; experience with SonarQube, dependency and container scanning, SAST/DAST, and/or Artifactory or Nexus isa plus
Strong code review experience, both providing and receiving reviews, as well as applying standards for correctness, security, testing and readability
Additional depth in AI/ML platforms such as Azure OpenAI, AWS Bedrock, Google Vertex AI, Anthropic Claude API, MLflow, Azure Machine Learning, or SageMaker is a plus
The pay range for the role is $150,000 to $205,000. The specific offer will depend on an applicant’s skills and other factors. This role may also be eligible to participate in a discretionary annual incentive program. Chubb offers a comprehensive benefits package, more details on which can be found on our careers website. The disclosed pay range estimate may be adjusted for the applicable geographic differential for the location in which the position is filled.
