> Markdown version of [/jobs/ext/4167137-agentic-al-architect](https://www.wearedevelopers.com/jobs/ext/4167137-agentic-al-architect). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Agentic Al Architect - **Company:** Robotics Technologies LLC - **Location:** Tampa, FL, United States - **Experience:** Expert - **Contract:** Temporary contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Amazon Web Services, Data Security, Identity and Access Management, Python (Programming Language), Knowledge-Based Systems, PostgreSQL, Next.js, Systems Integration, TypeScript, Management of Software Versions, Data Logging, Enterprise Software Applications, User Controls, Retrieval-Augmented Generation, Multi-Agent Systems, Prompt Engineering, AgentCore, Backend, Agentic-AI, Build Management, Containerization, Kubernetes, Cloudwatch, Human in the Loop, Docker, Natural Language Generation - **Published:** October 31, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=028488de8f2040e9 ## About the Role We are looking for a hands-on Senior Agentic Al Architect with deep expertise in AWS AgentCore, Context Engineering, and Harness Engineering to design, build, and deploy enterprise-grade Al assistants and intelligent automation solutions. The role requires strong experience in building production-ready agentic systems, integrating enterprise knowledge sources and applications, and developing secure, scalable solutions on AWS. The candidate should be comfortable owning the complete development lifecycle, from solution design and implementation to deployment and optimization, while delivering quickly based on business priorities. Key Responsibilities: Must Have: * Agentic Al Development: Design and build intelligent Al agents capable of reasoning, planning, tool execution, and managing complex workflows with minimal human intervention. * AWS AgentCore (Mandatory): Hands-on experience building and deploying agents using AWS AgentCore, including Runtime, Memory, Gateway, Identity, Policy, and Observability capabilities. * AWS - Bedrock (Must Have) * Context Engineering (Mandatory): Design effective context management strategies covering memory retrieval, conversation summarization, knowledge injection, prompt versioning, and context window optimization. * Harness Engineering (Mandatory): Build reliable agent execution frameworks with tool-call orchestration, retry handling, structured output validation, capability routing, and automated testing.Multi-Agent Orchestration: Develop and coordinate specialized Al agents using frameworks such as LangGraph Preferred: * Strands Agents, including task delegation, state management, and workflow execution. ## Description * Proactive Al Automation: Build event-driven agents that can monitor relevant activities, identify actionable information, generate notifications, draft communications, and initiate authorized workflows. * Enterprise Knowledge & RAG: Develop knowledge ingestion and retrieval pipelines using PostgreSQL, pavector, and RAG techniques, with appropriate knowledge governance and access controls. * MCP & Enterprise Integrations: Build MCP servers and clients to connect agents with enterprise applications, APIs, communication platforms, and internal knowledge systems. * AWS Cloud Engineering: Design and implement solutions using AWS IAM, Secrets Manager, ECR, Aurora PostgreSQL, SOS, EventBridge, and CloudWatch. * EKS & Containerization: Deploy and manage FastAP! and Next.js applications on Amazon EKS using Docker, Kubernetes, Helm, autoscaling, ingress, and AgentCore connectivity. * Full-Stack Development: Develop backend services using Python/FastAP! and frontend applications using Next.js and TypeScript. * Security & Access Management: Implement enterprise SSO, Cedar/ABAC policies, fine-grained authorization, secure data handling, and protection against unauthorized agent actions. * Human-in-the-Loop: Implement approval mechanisms and user controls for Al-generated communications, recommendations, and sensitive automated actions. * Agent Memory & State Management: Build persistent memory, personalized context, conversation continuity, and reliable asynchronous workflows with checkpointing and failure recovery. * Testing & Observability: Establish agent evaluation, execution tracing, monitoring, logging, and testing to ensure accuracy, reliability, security, and performance. * End-to-End Ownership: Take ownership of architecture, hands-on development, integration, testing, and deployment, with a strong focus on practical solutions, engineering quality, and rapid delivery.