AWS Agentic AI Architect / Lead

Role Summary

We are looking for an experienced AWS Agentic AI Architect / Lead with strong hands-on expertise in designing and implementing production-scale Agentic AI and Generative AI solutions on AWS.

The ideal candidate should have 10+ years of experience in designing distributed applications, with at least 3+ years of strong hands-on experience in Generative AI and multi-agent system design.

The candidate will be responsible for architecting and building enterprise-grade agentic solutions using Amazon Bedrock, AWS AgentCore, AgentCore Runtime, AgentCore Gateway, Knowledge Bases, SageMaker and other AWS AI/ML services.

The role requires a combination of architecture leadership and hands-on engineering, with strong expertise in Python or TypeScript, agent frameworks, enterprise security, API integration, observability and AI platform engineering.

Primary Skills

• AWS Bedrock
• AWS AgentCore
• AgentCore Runtime
• AgentCore Gateway
• AgentCore Identity
• Amazon Bedrock Knowledge Bases
• Intelligent Agent Development
• Agentic AI Architecture
• Multi-Agent Systems
• Generative AI
• RAG Architecture
• LLM Integration

Secondary Skills

• Python / TypeScript
• LangGraph
• CrewAI
• LlamaIndex
• AWS SageMaker
• AWS AI/ML Services
• Cloud Architecture
• Enterprise API Integration
• MCP
• AWS IAM
• AI Platform Engineering
• Observability & Evaluation

Key Responsibilities

1. Agentic AI Architecture

• Design and build autonomous, multi-step Agentic AI workflows for enterprise use cases.
• Architect distributed multi-agent systems capable of interacting with enterprise data, APIs and business systems.
• Define scalable architecture patterns for production-grade Generative AI and Agentic AI solutions.
• Provide technical leadership while remaining hands-on with implementation.

2. AWS Bedrock & AgentCore

• Design and implement Agentic AI solutions using Amazon Bedrock and AWS AgentCore.
• Transition agentic applications from local or development environments to production-scale deployments using AgentCore Runtime and managed AWS services.
• Utilize AgentCore capabilities for runtime isolation, long-running workloads and memory/context awareness.
• Architect solutions using AgentCore CLI and associated services.

3. Agent & Tool Integration

• Expose existing enterprise APIs and AWS Lambda functions as agent-ready tools.
• Implement integrations using AgentCore Gateway and Model Context Protocol (MCP).
• Design tool-calling architectures that enable agents to securely interact with enterprise applications.
• Integrate agents with enterprise APIs, data platforms and backend systems.

4. AI Orchestration & Frameworks

• Develop and architect solutions using LangGraph, CrewAI and LlamaIndex.
• Design flexible orchestration architectures that support multiple agent frameworks.
• Ensure seamless deployment and management of agentic applications through AWS AgentCore.

5. Security & Identity Management

• Design secure end-to-end architectures for enterprise AI workloads.
• Implement AWS IAM-based access controls and identity management.
• Define security boundaries, authentication and authorization mechanisms.
• Implement role-based access controls and policy enforcement.
• Ensure protection of AI pipelines and enterprise data.
• Apply encryption for data at rest and in transit.
• Implement secure API management within AI and agentic workflows.
• Utilize AgentCore Identity capabilities where applicable.

6. RAG & Knowledge Architecture

• Design and implement Retrieval-Augmented Generation (RAG) architectures.
• Develop solutions using Amazon Bedrock Knowledge Bases.
• Integrate enterprise data sources with AI applications.
• Optimize retrieval, context management and LLM response generation.
• Ensure enterprise data is securely accessed by agents and LLM applications.

7. Observability & AI Evaluation

• Implement real-time telemetry and tracing for Agentic AI applications.
• Establish monitoring and observability for agent workflows.
• Design continuous AI quality evaluation pipelines.
• Monitor agent performance, reliability and workflow execution.
• Identify and resolve production issues across distributed AI systems.

8. Production Engineering

• Build scalable, reliable and production-ready Agentic AI applications.
• Troubleshoot issues across AI applications, cloud infrastructure, APIs and agent workflows.
• Ensure high availability, scalability and performance of AI platforms.
• Establish engineering standards and best practices for enterprise AI deployments.

Mandatory Technical Skills

Candidates must have strong hands-on experience with:

• AWS AI Services
• Amazon Bedrock
• AWS AgentCore
• AgentCore Runtime
• AgentCore Gateway
• AgentCore Identity
• Bedrock Knowledge Bases
• Agentic AI / Intelligent Agent Development
• Generative AI
• Multi-Agent Systems
• RAG Architecture
• LLM Integration
• Python or TypeScript
• Distributed Application Architecture
• AWS Cloud Architecture
• AWS IAM and Security
• Enterprise API Integration

Preferred Experience

• 10+ years of experience in software or distributed application architecture.
• 3+ years of strong hands-on experience in Generative AI and Agentic AI.
• Hands-on experience taking agentic applications from POC or local environments to production.
• Experience with LangGraph, CrewAI or LlamaIndex.
• Experience with MCP (Model Context Protocol).
• Experience integrating Lambda and legacy or enterprise APIs with agentic systems.
• Experience with AWS SageMaker and other AWS AI/ML services.
• Experience designing AI observability and evaluation frameworks.
• Experience working on enterprise-scale AI platforms.

Education

• Bachelor's Degree in Computer Science, Information Technology, Engineering or a related field.

Soft Skills

• Strong communication skills.
• Excellent presentation and stakeholder-management abilities.
• Strong architectural and analytical thinking.
• Ability to explain complex AI concepts to technical and business stakeholders.
• Strong problem-solving skills.
• Team player with the ability to work across architecture, engineering, security and business teams.
• Ability to provide technical leadership while remaining hands-on.

Ideal Candidate Profile

The ideal candidate is an AWS-focused AI Architect / Technical Lead who combines strong distributed systems architecture experience with deep, practical expertise in Agentic AI and Generative AI.

The candidate should be capable of designing the architecture, making AWS service decisions, implementing AgentCore-based solutions, integrating enterprise tools and APIs, establishing security and observability, and guiding the engineering team through production deployment.

Candidate Screening Questions

1. How many years of hands-on experience do you have with Generative AI and Agentic AI, and specifically with Amazon Bedrock and AWS AgentCore?
2. Have you designed and deployed production-scale multi-agent systems using AgentCore Runtime, AgentCore Gateway, Knowledge Bases or AgentCore Identity?
3. What is your hands-on experience with Python or TypeScript and agent frameworks such as LangGraph, CrewAI or LlamaIndex, particularly for RAG, LLM integration and enterprise API/tool integration?
4. Are you comfortable working from the Hyderabad location in a Hybrid/Onsite model under a 12-month extendable contract-to-hire contract?