Software Engineer; UI & Applied AI

Overview

Staff Software Engineer - IE07IE

We’re determined to make a difference and are proud to be an insurance company that goes well beyond coverages and policies. Working here means having every opportunity to achieve your goals – and to help others accomplish theirs, too. Join our team as we help shape the future. The Hartford is seeking a Staff Software Engineer (UI & Applied AI) to join the Innovation Value Stream within Personal Lines—an area where engineers help set the trend for AI platforms across the PL business.

This is a rare opportunity to work on a greenfield initiative, shaping how The Hartford designs and delivers next‑generation AI‑enabled user experiences.

Role

In this role, you will define and build the UI foundation for emerging AI and agentic capabilities, including chat experiences, AI assistant panels (copilots), file‑upload for RAG pipelines, agent tools, MCP‑based interactions, and integration with API gateways exposing agent ADK runner. You will work directly with a collaborative, product‑based team that values:

• Rapid prototyping to prove ideas early
• Enterprise best practices and alignment with EA and AI governance
• Continuous learning and experimentation
• Delivering cutting‑edge experiences that create measurable value for cross‑functional Personal Lines users (pricing analysts, CSRs, inspection contractors, underwriting, and product partners)

This role offers the opportunity to make a significant strategic and technical impact, influencing the future of AI‑driven application experiences across the Personal Lines organization.

Responsibilities

• Define and evolve the UI platform strategy, ensuring extensibility, future‑proofing, and readiness for rapidly emerging AI capabilities (interact with agent workflows, interactive chat, Agent 2 Agent, agent tool use selection, RAG workflows).
• Provide technical leadership, maintaining architectural alignment and the integrity of the UI platform and application environment.
• Collaborate with platform teams to safely leverage AI and agentic capabilities through stable, versioned APIs and shared governance.
• Champion innovation, experimenting with modern frameworks, architectures, and AI‑driven enhancements that improve user experience and accelerate delivery.
• Partner with Product, Design, Architecture, Data Science, and Platform teams to evolve ideas from POCs → MVPs → scalable production experiences.
• Design human‑in‑the‑loop workflows (approve/override/rollback, review gates, clear status indicators) to ensure safe and transparent AI decision‑making.
• Plan integration patterns for GCP Agent SDK/Agent Builder, AWS Bedrock/Anthropic, Snowflake/data products, and retrieval/embedding pipelines using typed SDKs/APIs.
• Architect AI UX patterns such as copilots, chat flows, inline recommendations, tool‑triggering actions, and token‑streaming guidance with cancel/retry and partial updates.
• Define prompt templates, guardrails, and explainability signals (confidence, sources, metadata) for safe AI usage directly in the UI flows.
• Lead hands‑on UI development in Type Script using Angular and/or React, delivering modern single‑page applications across CSR, SSR, and hybrid rendering models (Angular Universal, Next.js).
• Build AI‑driven user interaction surfaces: side panels, chats, inline instruction flows, streaming experiences, and contextual tool invocation.
• Develop file‑upload and document‑management interfaces integrated with RAG pipelines, presenting detailed ingestion lifecycle statuses (uploaded → queued → extraction → embedding → retrieval‑ready → processed).
• Integrate UI components with MCP (Model Context Protocol), agent tools, and API gateways, supporting multi‑step agent workflows (planning → executing → tool call → validating → complete → error).
• Improve UI performance through modular routing, lazy loading, optimal async patterns, reduced bundle sizes, efficient rendering, and clean component architecture.
• Apply strong engineering practices: unit tests, integration tests, E2E, visual regression, prompt regression, and streaming/real‑time test harnesses.
• Monitor real‑world performance and reliability using Dynatrace, Google Analytics, Cloud Logging, and…