Senior AI Developer with Model Context Protocol
About the Position
We are looking for a Senior AI Developer to help design and implement core capabilities for an agent platform. You will work on protocol based tool integration, secure agent interactions, and platform components that support scalable agentic workflows.
About the Project
The Agent Platform is focused on enabling AI agents to discover, access, and use tools in a secure and scalable way. It covers protocol based tool integration, agent to agent communication, semantic search, and policy driven authorization for enterprise AI environments.
Responsibilities
- Design tool integration layers for AI agents
- Implement Model Context Protocol or similar agent tool protocols
- Develop semantic tool discovery using embedding based search
- Build authorization flows for tool calls and agent interactions using policy enforcement
- Implement JWT based cross agent authentication and identity federation
- Configure AWS Bedrock AgentCore Gateway for MCP target registration, HTTP target routing, and inference target configuration
- Collaborate on multi agent orchestration and agent to agent communication patterns
- Support enterprise security reviews for AI systems, including authorization, data access, and audit
Requirements
- 5+ years of experience building AI or ML platforms or agentic systems
- Experience designing tool integration layers for AI agents, including function calling and tool use
- Experience implementing Model Context Protocol or similar agent tool protocols
- Experience with enterprise security reviews for AI systems, including authorization, data access, and audit
- Knowledge of agentic workflow patterns, including agent to tool communication, agent to agent communication, and multi agent orchestration
- Experience with semantic tool discovery and embedding based search
- Experience with agentic authorization and policy enforcement
- Experience with JWT based cross agent authentication and identity federation
- Experience with AWS Bedrock AgentCore Gateway
Nice to Have
- Experience building multi agent systems with agent to agent communication
- Experience with semantic search using embeddings, FAISS, Pinecone, or vector databases
- Hands on experience with AWS Bedrock Agents or AgentCore
- Experience with agentic gateway topology design, including central and federated models and tool visibility scoping
- Experience with credential vending for agents, including 3LO OAuth and per tool authentication
Technologies
Model Context Protocol, Agent to agent communication, Multi agent orchestration, Embedding based semantic search, Cedar policy language, JWT, Entra Agent ID, AWS Bedrock AgentCore Gateway, FAISS, Pinecone, Vector databases, OAuth
