Senior Software Engineer

Chubb•Jersey City, NJ

About The Position

As a Senior Software Engineer on Chubb’s Ingestion Platform team, you will help rebuild how digital products are delivered to customers and partners worldwide. You will design and build platform services, workflows, AI capabilities, and data pipelines, own features from design through production, and help shape your team’s technical direction. You will collaborate with architects, data scientists, product owners, and business stakeholders in an insurance environment where reliability, privacy, security, and regulatory discipline are essential. The role offers the opportunity to shape core platform decisions and deliver scalable systems that support intelligent, resilient digital experiences. You will build scalable services and APIs; durable workflows and agentic AI features; and capabilities for retrieval-augmented generation, memory, ontologies, and document processing. You will protect AI and retrieval inputs, evaluate and monitor AI features, integrate with internal systems and external partners, and support software delivery through CI/CD pipelines, code reviews, and cloud-native automation. You will also mentor engineers and contribute to technical standards and architecture reviews.

Requirements

At least 8 years of software engineering experience, including at least 3 years building distributed, data-intensive, or platform systems in production.
Bachelor's or Master's degree in Computer Science, Engineering, or a related field, or equivalent experience.
Strong programming skills in Python, Java, Scala, or a similar language, and strong SQL skills.
Experience with microservices, APIs, and event-driven architecture on AWS, Azure, or GCP.
Solid distributed systems fundamentals, including idempotency, retries and backoff, circuit breakers, consistency, structured logging, distributed tracing, and correlation IDs.
Experience with streaming technologies such as Kafka, Kinesis, or Event Hubs and distributed data processing such as Spark, Flink, or Beam.
Experience with data modeling for SQL and NoSQL stores.
Hands-on experience with LLM-based applications, including at least one production or serious prototype using RAG or agents with tool calling.
Working knowledge of ontologies or knowledge graphs and data science and ML basics, including the Python data stack, model evaluation, and how models are deployed and monitored.
Hands-on CI/CD experience building and maintaining Jenkins pipelines with automated test, scan, and release stages, and Git workflows with pull requests.
Strong code review experience, both giving and receiving reviews, and applying standards for correctness, security, testing, and readability.

Nice To Haves

Knowledge of or experience with insurance processes, regulatory requirements, and industry standards.
Experience with Kubernetes, Docker, Terraform, and/or GitOps.
Experience with Temporal, Camunda, AWS Step Functions, and/or Cadence.
Experience with Delta Lake, Iceberg, data governance, and/or metadata management.
Experience with LangGraph, AutoGen, CrewAI, Claude Agent SDK, MCP, and LLM evaluation and/or observability tools.
Experience with Neo4j, MongoDB, GraphDB, JSON-LD, SHACL, Cypher, SPARQL, and/or Gremlin.
Experience with SonarQube, dependency and container scanning, SAST/DAST, and/or Artifactory or Nexus.
Additional depth in AI/ML platforms such as Azure OpenAI, AWS Bedrock, Google Vertex AI, Anthropic Claude API, MLflow, Azure Machine Learning, or SageMaker.

Responsibilities

Design and build scalable services and APIs with clear contracts, idempotency, retries, and failure isolation.
Deliver features from user stories and acceptance criteria through production using an agile SDLC.
Contribute to design and architecture reviews and propose improvements to standards and tooling.
Write clean, testable, observable code with unit, integration, and contract tests.
Integrate with internal systems and external partners through governed APIs, event streams, and webhooks, including schema versioning.
Build durable workflows and agentic AI features, including human-in-the-loop steps, tool calling, MCP, and guardrails.
Evaluate and monitor AI features using 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 through document access control, PII/PCI redaction, and defenses against prompt injection while following security, privacy, and regulatory requirements.
Build and maintain CI/CD pipelines and manage branching and release practices.
Review code thoroughly, keep pipelines healthy, resolve root causes, mentor engineers, and improve cloud-native automation where useful.