Sr. Software Engineer – AI and Automation (Team Breeze)

Travelers • Hartford, CT

6d

About The Position

The Sr. Software Engineer on Travelers’ Team Breeze builds and operates production AI applications at the intersection of large language models, cloud-native infrastructure, and business needs. The role focuses on LLM agents, retrieval pipelines, and production reliability, including end-to-end ownership of retrieval-augmented generation workflows and services across AWS, Kubernetes, Python, TypeScript/Node, and React. The engineer also leads complex technical work, resolves critical production issues, and provides guidance and mentorship to teammates.

Requirements

• Bachelor’s degree in computer science, a related STEM field, or equivalent education and/or work experience.
• Six additional years of software engineering experience.
• Demonstrated experience shipping LLM or agent systems to production.
• Hands-on knowledge of tool calling, prompt and routing design, RAG retrieval quality tuning, and defining evaluations to measure LLM and retrieval performance.
• Strong AWS serverless and EKS experience, including designing and debugging production systems spanning Lambda, API Gateway, and Kubernetes-based containers.
• Practical experience authoring and maintaining Terraform, Helm charts, and CI/CD pipelines such as GitHub Actions and TEP.
• Observability experience with OpenTelemetry or Dynatrace, structured logging with correlation IDs, cost tracking, and incident handling.
• Comfort working across Python and TypeScript/Node 24 in the service layer and React 19/Vite on the front end.
• Familiarity with data and retrieval pipelines from ingestion through embedding to vector-store-backed APIs.
• Consistent practice of writing tests, evaluations, and data-quality checks.
• Ability to determine software design strategy and methodology, use automated tests and feedback loops to ensure quality and production readiness, and monitor work efforts and adjacent systems.
• Track record of developing business partnerships and influencing priorities by identifying solutions aligned with business objectives; follows relevant industry trends and shares knowledge with coworkers.
• Strong problem-solving skills, including using data and proofs of concept, measuring impact, reflecting on outcomes, and optimizing solutions involving many factors and broad implications.
• Ability to explain technology to business audiences, document initiatives clearly and concisely, collaborate across roles, give and receive constructive feedback, and listen attentively and empathetically.
• Leadership skills, including taking action without clear ownership, inspiring and motivating others, and influencing team members.

Nice To Haves

• Experience with Strands, LangGraph, or Bedrock AgentCore.

Responsibilities

• Lead the design, configuration, and development of complex, high-visibility AI applications on Team Breeze, focusing on LLM agents, retrieval pipelines, and production reliability.
• Design and implement agent orchestration flows using AWS Bedrock AgentCore and/or frameworks such as LangGraph, including tool calling, routing, and prompt strategies for Claude models on Bedrock.
• Own the RAG pipeline from document ingestion through processing, embedding, and vector-store-backed retrieval APIs, including evaluation of retrieval and answer quality before releases.
• Architect and build AWS services using Lambda, API Gateway, S3, CloudFront/Lambda@Edge, Route 53, Secrets Manager/Vault, and Bedrock application inference profiles for cost tracking and management.
• Develop and operate containerized retrieval and evaluation services on Amazon EKS, deployed with Helm and ArgoCD, with OpenTelemetry traces exported to Dynatrace, S3, and Braintrust.
• Implement and maintain infrastructure as code and CI/CD using Terraform, Terraform Enterprise, GitHub Actions, and TEP pipelines.
• Build and maintain application services across Python and TypeScript/Node 24, as well as front-end experiences using React 19/Vite.
• Lead investigation and resolution of critical, high-impact production issues across AWS services, Kubernetes workloads, data pipelines, and observability tooling.
• Provide technical guidance and mentorship, promoting sound practices for design documentation, testing, evaluations, code reviews, and operational readiness.
• Apply current AI/LLM, cloud, and observability knowledge to improve system design, developer productivity, and business outcomes.
• Perform other duties as assigned.

Benefits

• Health insurance coverage for eligible employees and family members beginning on the first day of employment.
• Dollar-for-dollar 401(k) matching on contributions up to the first 5% of eligible pay, subject to an annual maximum.
• Paying it Forward Savings Program, with annual employer contributions to a 401(k) when employees make student loan payments.
• Pension Plan funded 100% by Travelers.
• Minimum of 20 days of paid time off annually.
• Nine paid company holidays.
• Wellness program with tools, discounts, and resources supporting wellness goals and caregiving needs.
• Mental health program offering free professional counseling, health coaching, and other resources.
• Matching Gift and Volunteer Rewards program.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior