Назад до пошукуLead Python Engineer — MCP Protocol & Tool Integration
*Ви можете працювати віддалено з території країни (або країн), для яких відкрита ця позиція.
We are looking for a Lead Python Engineer to join our team and drive the development of an Enterprise Agent Development Platform — a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The platform standardizes agent development across the organization using LangGraph and Strands Agents on AWS AgentCore Runtime. The initiative spans agent framework design, runtime architecture, marketplace integration, CI/CD automation, and enterprise-grade observability — reducing agent development from months to days while enforcing consistent security, quality, and governance standards.
- Implement MCP protocol servers and clients, including tools/list and tools/call handling and capability negotiation
- Design and build agent tool integrations using function calling, tool schema definition, and parameter validation
- Develop async HTTP services and streaming responses for MCP server/client communication
- Integrate MCP target types such as Lambda functions as tools, remote MCP servers, and OpenAPI-to-MCP translation
- Manage tool metadata, including schema registration, capability tagging, and versioning
- Register targets with AWS AgentCore Gateway to expose tools to agent systems
- Collaborate with engineering teams to standardize agent tool integration patterns across the platform
- Translate OpenAPI specifications into MCP-compliant tool definitions
- Ensure tool integrations meet enterprise-grade security, quality, and governance standards
- Hands-on experience implementing MCP (Model Context Protocol) servers or clients in a production agentic AI project, such as tools/list and tools/call handling, AWS AgentCore Gateway target registration, or Lambda-as-tool / OpenAPI-to-MCP translation
- 5+ years of Python engineering experience with agent/AI systems
- Experience building tool integrations for LLM agents, such as OpenAI functions, LangChain tools, or equivalent
- Expertise in async HTTP services and streaming protocols implementation
- Background in AWS Lambda development
- Proficiency in English at a B2+ level
- Experience with MCP protocol implementation (server or client)
- Familiarity with LangChain / LangGraph tool integration
- Experience with AWS Bedrock AgentCore Gateway target registration
- Knowledge of semantic tool indexing, including embedding generation for tool descriptions
- Familiarity with agent framework integration (Strands, Crew, AutoGPT)