About this role
This position is part of the AWS Specialist and Partner Organization (ASP). Specialists own the end-to-end go-to-market strategy for their respective technology domains, providing the business and technical expertise to help our customers succeed. The Agentic WorkSpaces Solutions Architect team is seeking a hands-on, customer-obsessed Solutions Architect to accelerate customer adoption of agentic AI capabilities built on Amazon WorkSpaces. This team operates as a dedicated advisory and hands-on development function — assigning engineering resources directly to customers to achieve production-ready outcomes in weeks instead of months. As an Applied AI Solutions Architect, you will be embedded with customers to help them prepare their Agentic WorkSpaces implementations for production. Your work centers on three pillars of agentic AI: Model Selection — Guiding customers through evaluating and selecting the right foundation models (via Amazon Bedrock) for their workspace use cases, balancing latency, accuracy, cost, and compliance requirements. Prompt Configuration — Designing, testing, and optimizing AI prompts and system instructions for agentic workspace AI, including self-service agents, recommendation agents, and custom orchestrator agents. Tool Configuration — Architecting and building the tool integrations (APIs, Lambda functions, data connectors, knowledge bases) that agentic AI systems use to take actions on behalf of users — including configuring MCP (Model Context Protocol) servers for standardized tool discovery and invocation and enabling A2A (Agent-to-Agent) communication patterns for multi-agent orchestration across enterprise systems. A critical dimension of this role is Customer Data Readiness — assessing, preparing, and structuring customer data assets so that AI agents can reliably access, retrieve, and act on the right information. The delivery substrate for this work is Virtual Desktop Infrastructure (VDI) and Desktop-as-a-Service (DaaS). You must understand the architecture, networking, identity, and operational patterns of virtualized desktop environments — because that is where these AI agents operate and where customers derive value. You will work at the intersection of end-user computing and applied AI, helping customers move from proof-of-concept to production for their Agentic WorkSpaces deployments. This is a deeply technical, hands-on role. You will write code, build integrations, configure agents, and pair-program with customer engineering teams. This role operates as forward deployed engineering. You will co-build AI solutions directly alongside customer developers — not hand off reference architectures and walk away. Per the Customer Deployment Engineering ) methodology, you will navigate dev and test environments with the customer, validate configurations under real workload conditions, and identify production blockers before they surface. You will leverage these engagements to advise customers on production rollouts of WorkSpaces Agent Access — transitioning validated prototypes into fully operational agentic desktop environments at scale. Willingness to travel up to 25–40% for on-site customer engagements. Key job responsibilities You will lead technical discovery sessions with customer teams to understand business requirements, existing desktop infrastructure, and AI readiness. You translate findings into actionable implementation plans that move customers from evaluation to production deployment. You will design and configure agentic AI solutions within Agentic WorkSpaces, including AI agent creation, prompt engineering, and tool/action integration. You will build serverless integrations using AWS Lambda, API Gateway, Step Functions, and scripting (Python, Node.js). You will architect secure access patterns to cloud-based data systems (e.g. Amazon DynamoDB, Amazon RDS, Amazon S3, Knowledge Bases for Bedrock) to power AI agent tool use and retrieval-augmented generation (RAG). You will work with customers to deploy Amazon WorkSpaces Personal, Pools and Amazon WorkSpaces Applications as the delivery platform for agentic AI experiences. You will guide customers through testing, evaluation, and validation of AI agent performance against defined success criteria before production deployment. You will create reusable artifacts — reference architectures, implementation guides, sample code, prompt libraries, data readiness checklists — that scale best practices across the SA community and partner ecosystem. You will provide Voice-of-Customer feedback to the Agentic WorkSpaces Service Team based on real-world customer implementations, contributing to product roadmap prioritization. A day in the life You pair-program with customer developers to build and test AI agent configurations deployed on WorkSpaces environments. You design prompt strategies and evaluate model performance across different foundation models. You configure MCP servers to expose customer APIs, databases, and tools in a standardized format for agent consumption. You design A2A workflows where workspace agents hand off to or collaborate with specialized agents across the customer’s enterprise. You deploy and validate WorkSpaces architectures to ensure the desktop substrate is production-ready. You configure knowledge bases and data connectors for RAG-powered agent responses. You conduct architecture reviews and provide prescriptive guidance for production readiness. You document implementation patterns and contribute to the team’s knowledge base. You participate in weekly syncs with service teams to share customer feedback and product insights.