This position sits within the AWS Specialist and Partner Organization (ASP). Specialists own the end-to-end go-to-market strategy for their technology domains and provide the business and technical expertise that helps our customers succeed. Partner teams own the strategy, recruiting, development, and growth of our key technology and consulting partners. Together, they give our customers the expertise and scale they need to build innovative solutions for their most complex challenges.

Customer experience is being reinvented by applied AI, and Amazon Connect sits at the center of that shift. Our team turns the newest Amazon Connect AI capabilities into working systems and hands-on experiences that customers, sales teams, and partners can actually use. What we build shortens the path from "is this possible?" to "here's how it works," accelerates adoption of applied AI on Amazon Connect, and feeds real-world signal back into the product roadmap. The reference architectures, demos, and internal assets you create are often the first thing a customer sees, and the fastest way a global sales team can show the art of the possible.

The Applied AI Solutions Architecture team is hiring a hands-on Solutions Architect to design and deliver AI-first solutions on Amazon Connect. The role has two halves: you build working systems, reference architectures, and internal assets that advance org-level initiatives, and you build Live demos that let sales teams, customers, and partners use production-quality Amazon Connect AI agents.

You work across the full stack, from the user-facing experience down to the integrations and data behind it, anchored on Amazon Connect. The work covers five areas:

Prompt configuration: Design, test, and tune prompts and system instructions for Amazon Connect AI agents, including self-service agents, answer recommendation agents, and custom orchestrator agents. Evaluate LLM behavior and tune for reliable performance.

Agent memory and context: Build short-term, long-term, and session memory, manage context windows, and structure state so agents stay coherent and personalized across multi-turn and multi-agent interactions.

Tool configuration: Build the integrations agents use to take action (APIs, Lambda functions, data connectors, knowledge bases), configure MCP (Model Context Protocol) servers for standardized tool discovery and invocation, and enable A2A (Agent-to-Agent) patterns for multi-agent orchestration.

Data readiness: Assemble and structure realistic datasets and knowledge bases (sample CRMs, ticketing systems, order management) so agents retrieve and act on the right information.

Well-Architected: Apply the AWS Well-Architected Framework across operational excellence, security, reliability, performance efficiency, cost optimization, and sustainability.

Key job responsibilities

- Org initiatives: Deliver AI-first solutions for org-level initiatives, including working systems, reusable reference patterns, and internal assets on Amazon Connect that help the broader organization adopt applied AI.

- Live demos: Design, build, and maintain Live demo environments showcasing Amazon Connect AI agents. Turn emerging use cases and new product capabilities into hands-on experiences.

- Full-stack development: Build front-end experiences and back-end services, write REST APIs and web services, and integrate agentic and generative AI into working applications.

- Agent development: Configure Amazon Connect AI agents end to end, covering agent creation, prompt engineering, guardrails, LLM evaluation and tuning, and memory and context management across turns and sessions.

- Tools and multi-agent orchestration: Deploy MCP servers that expose tools, data sources, and APIs in a standardized format for dynamic discovery and invocation. Architect A2A patterns so Connect agents collaborate with specialized agents for billing, order management, and IT support.

- Integrations and data: Build serverless integrations with AWS Lambda, API Gateway, and Step Functions in Python and Node.js. Architect secure access to Amazon DynamoDB, RDS, S3, OpenSearch, Kendra, and Knowledge Bases for Amazon Bedrock for agent tool use and RAG.

- Security and Well-Architected: Apply least-privilege access, data protection, and guardrails, account for HIPAA and GDPR where relevant, and hold every solution to the Well-Architected pillars.

- Validation: Test and evaluate agent performance against defined success criteria so each solution and demo is reliable and repeatable.

- Knowledge sharing: Create reusable artifacts (reference architectures, playbooks, sample code, prompt libraries, data readiness checklists) for the Amazon Connect SA community and partner ecosystem.

- Service team collaboration: Share what you learn with the Amazon Connect and Amazon Bedrock product teams and contribute to roadmap prioritization.

A day in the life

- Build and test Amazon Connect AI agent configurations for internal solutions and Live demos.

- Write front-end code, REST APIs, and back-end services.

- Tune prompts and agent memory, then evaluate the results against your success criteria.

- Configure MCP servers and A2A handoffs, and wire up knowledge bases for RAG.

- Review a teammate's demo and give prescriptive guidance.

- Document patterns, and join the weekly Amazon Connect service team sync.

BASIC QUALIFICATIONS

- 7+ years of specific technology domain areas (e.g. software development, cloud computing, systems engineering, infrastructure, security, networking, data & analytics) experience

- 3+ years of design, implementation, or consulting in applications and infrastructures experience

- 3+ years of hands-on coding experience with REST APIs and web services, including integrating agentic or generative AI into working applications.

- Full-stack development experience across front-end and back-end.

- Cloud experience (AWS preferred) across compute, database, integration, identity, networking, and automated packaging and deployment.

- Hands-on experience with large language models (LLMs), prompt engineering, agent memory and context management, retrieval-augmented generation (RAG), and model evaluation.

- Familiarity with MCP (Model Context Protocol) and A2A (Agent-to-Agent) interoperability protocols.

PREFERRED QUALIFICATIONS

- Knowledge of security and compliance standards including HIPAA and GDPR

- Hands-on experience with Amazon Connect and its AI capabilities.

- Hands-on experience with Amazon Bedrock, including model invocation, agent creation, knowledge base configuration, and guardrails.

- 2+ years designing and implementing conversational AI (voice or chat) with a framework such as Amazon Lex.

- Experience with agentic AI patterns such as multi-agent orchestration, tool use, function calling, chain-of-thought reasoning, and autonomous agent workflows.

- Experience building and deploying MCP servers that expose enterprise tools and APIs for dynamic agent tool discovery.

- Experience applying the AWS Well-Architected Framework to production systems.

- Experience with automation and scripting (for example, Terraform and Python).

- Experience building demos, proofs-of-concept, or interactive product experiences.

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, NY, New York - 169,000.00 - 228,600.00 USD annually

USA, TX, Austin - 153,600.00 - 207,800.00 USD annually

USA, WA, Seattle - 153,600.00 - 207,800.00 USD annually