What you will lead:

A reimagined enrollment experience where AI is a strategic partner for employees making benefit decisions. Rather than walls of plan text, it understands who someone is - family situation, population segment, geography, past elections - and delivers personalized plan recommendations, real cost-per-paycheck impact, and coverage comparisons in plain language. Agentic MCP tools let employees self-serve enrollment actions through natural-language conversation: staging elections, handling qualifying life events, and managing dependent verification, all without navigating a portal.

A reinvented Benefits Management Console (BMC) that transforms how call-center agents support enrollment for a workforce of millions. The next-generation BMC surfaces the employee's full context instantly, displays intelligent adaptive workflows that adjust to case complexity, recommends next-best-actions for edge cases, automates routine verification and notification workflows, and learns from every resolution. The goal: dramatically reduce average call handling time and let agents focus on judgment and empathy rather than system navigation.

You will be the tech lead across both experiences, owning the shared architecture that powers personalized enrollment across all surfaces and the agentic foundations that let AI participate meaningfully in both employee self-service and agent-assisted workflows.

We build AI-native. In our model, humans own judgment and agents own the mechanical middle. Engineers write the specification and set the acceptance criteria; agents (Claude Code, Kiro) write a growing share of the implementation, author tests, and resolve code-review comments; engineers direct, validate, and own what ships, and still hand-write the novel, ambiguous, and infrastructure-heavy work where models fall short.

As a Senior Software Development Engineer, you are the tech lead for your team's product. You lead a system of many features across its full lifecycle - enrollment orchestration (BFF on Apollo GraphQL serving four surfaces), population-aware personalization, agentic tool architectures (MCP-based chatbot tools with consent handling and multi-turn state management), and next-generation agent workflow systems. You own the team-level architecture, make the high-stakes decisions, and review others' work - human-authored and agent-authored alike. You stay hands-on in the code and code reviews that matter most.

Key job responsibilities
• Lead your team's software development end to end: own the team-level architecture for enrollment orchestration, population-aware personalization, and agent console systems. Provide system-wide design guidance across all surfaces (mobile, web, chatbot, agent console) and make the high-stakes, hard-to-reverse technical decisions.
• Be the tech lead on large, ambiguous problems that span multiple organizations - enrollment flow architecture, agentic self-service, agent workflow reinvention, and claims-based plan simulation - where the customer direction is clear but the technology strategy is not. Drive clarity and align partner teams on the path forward.
• Own how AI participates in enrollment: design MCP tool contracts, multi-turn conversation state management, consent and authorization handling, confidence-based escalation, and the boundary between what AI does autonomously and where humans stay in the loop.
• Architect consent-gated, HIPAA-compliant pipelines for claims data ingestion and plan simulation - employee authorization frameworks, PHI handling, and personalized cost projections derived from actual utilization history.
• Architect the next-generation BMC that reduces call handling time: adaptive workflows that surface context and recommended actions, AI-driven automation of routine steps, and displays that adjust to case complexity and agent authorization level.
• Lead the team's AI Native build loops: define the specs, acceptance criteria, and simulation coverage that let agents safely take on more implementation work. Shape the agentic foundations (Bedrock AgentCore, MCP) the team builds on. Stay hands-on in the code and reviews that most affect the product.
• Lead and mentor engineers: coach multiple engineers on and off your team, drive adoption of engineering best practices, and hold human-authored and agent-authored work to the same high bar. Drive operational excellence including alarms, telemetry, runbooks, and root-cause resolution across team boundaries.
• Work backwards from the customer, bringing experience design judgment to technical decisions - partner with UX designers, technical writers, and communications strategists to ensure what gets built is also what gets understood and adopted by employees.

A day in the life

What the day-to-day looks like: you'll operate on a multidisciplinary team of SDEs, UX designers, and technical writers where every member owns real surface area - there are no inherited systems to passively maintain. Open enrollment dates are immovable, so you'll ship under genuine deadline pressure with genuine decision-making authority. You own production end to end, including on-call. You'll partner with UX designers on enrollment flows, collaborate with technical writers on how policy changes reach employees, and work with program managers to sequence delivery across teams. The technical breadth is uncommon: enrollment orchestration across four surfaces, a plan simulation engine ingesting claims data under HIPAA-compliant consent frameworks, population-aware personalization for corporate/WFM/operations employees, agentic chatbot tools for conversational self-service, and an agent console redesign aimed at cutting handle time in half - production agentic systems, regulated data engineering, experience orchestration, and AI-native methods in one seat.

This role is for tech leads who think in systems that serve people at sensitive moments - not just engineers who build features. You'll architect the full spectrum: from consent-gated pipelines that securely process claims data under HIPAA to the personalized recommendation surface that tells an employee "based on your family's actual usage, this plan saves you $1,200 next year." You'll own the boundary between what AI can do autonomously and where a human must stay in the loop. If you want to lead a team that ships production agentic systems, handles regulated health data with rigor, and measures success in reduced decision anxiety for employees and reduced handle time for agents - not just story points closed - this is a rare opportunity to own that end to end.

About the team

You will join Benefits Experience Technology (BXT), the Amazon organization reinventing how more than 1.5 million employees and their families experience benefits enrollment - and how the specialists who support them operate. Our vision is enrollment that is AI-powered, personalized, and proactive, and an agent console that is intelligent, workflow-driven, and fast.

BASIC QUALIFICATIONS

- 5+ years of non-internship professional software development experience

- 5+ years of programming with at least one software programming language experience

- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience

- Experience as a mentor, tech lead or leading an engineering team

PREFERRED QUALIFICATIONS

- 5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience

- Bachelor's degree in computer science or equivalent

- Experience building scalable, distributed, front-end experiences

- Experience developing, deploying and managing AI products at scale

- Experience architecting personalization or segmentation systems serving multiple user populations at scale

- Experience designing production agentic or conversational systems, including MCP tool architectures, multi-turn state management, and confidence-based escalation patterns

- Experience with GraphQL (Apollo Server preferred), React/TypeScript, and cloud-native infrastructure (AWS ECS, Lambda, API Gateway, DynamoDB, CloudFront)

- Demonstrated experience designing production systems that incorporate LLM-based agents, with frameworks such as Amazon Bedrock AgentCore, Model Context Protocol, Claude Code, or Kiro

- Experience building HIPAA-compliant systems or handling protected health information in production environments

- Track record of designing intelligent workflow systems for operational users with measurable impact on handle time or efficiency

- Experience in benefits, HR tech, fintech, or healthcare domains where decision-support UX and compliance requirements intersect

The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.

USA, WA, Seattle - 168,100.00 - 227,400.00 USD annually