Senior Python Engineer — MCP Protocol & Tool Integration

EPAM Systems; Polska; In loco; PLN 180.000 - 320.000; Tempo pieno

Vantaggi offerti da questo lavoro

Health insurance

Multisport

Shopping vouchers

Referral bonuses up to $2,000

Descrizione del lavoro

EPAM Systems in Poland is seeking a Senior Python Engineer to advance an Enterprise Agent Development Platform. You will implement MCP servers, design robust agent tool integrations, and register Lambda-based tools and remote MCP endpoints.

A strong focus on async HTTP, streaming, and tool schema validation supports scalable AI agent deployments. You will collaborate with cross-functional teams to standardize integration patterns, leverage LangGraph and LangChain tools, and ensure governance and

Competenze

• 5+ years of Python engineering experience with agent/AI systems.
• Experience implementing MCP servers or clients in production environments (tools/list, tools/call).
• Experience building tool integrations for LLM agents (OpenAI functions, LangChain).
• Proficiency in Python async programming, async HTTP services, and streaming protocols.
• Understanding of AWS Lambda development and tool integration patterns.

Mansioni

• Implement MCP protocol servers and clients, including tools/list and tools/call handling.
• Design and maintain agent tool integrations using function calling, tool schema definition, and parameter validation.
• Build and register MCP target types such as Lambda functions as tools, remote MCP servers, and OpenAPI-to-MCP translation.
• Develop async HTTP services and streaming responses for MCP server/client communication.
• Manage tool metadata, including schema registration, capability tagging, and versioning.
• Handle capability negotiation and Streamable HTTP transport within the MCP protocol.
• Collaborate with engineering teams to standardize agent tool integration patterns across the platform.
• Support AWS AgentCore Gateway target registration for agent tool connectivity.

Conoscenze

Python

Async programming

MCP protocol

OpenAI functions

AWS

Tool integration patterns

Formazione

Bachelor's degree in CS/SE

Strumenti

AWS Lambda

OpenAPI

LangChain

LangGraph

Strands

Crew

AutoGPT

Descrizione del lavoro

We are looking for a Senior Python Engineer to implement MCP protocol servers and agent tool integrations for 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 standardsResponsibilitiesImplement MCP protocol servers and clients, including tools/list and tools/call handlingDesign and maintain agent tool integrations using function calling, tool schema definition, and parameter validationBuild and register MCP target types such as Lambda functions as tools, remote MCP servers, and OpenAPI-to-MCP translationDevelop async HTTP services and streaming responses for MCP server/client communicationManage tool metadata, including schema registration, capability tagging, and versioningHandle capability negotiation and Streamable HTTP transport within the MCP protocolCollaborate with engineering teams to standardize agent tool integration patterns across the platformSupport AWS AgentCore Gateway target registration for agent tool connectivityRequirements5+ years of Python engineering experience with agent/AI systemsHands-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 translationExperience building tool integrations for LLM agents, such as OpenAI functions, LangChain tools, or equivalentProficiency in Python async programming, async HTTP services, and streaming protocolsExpertise in AWS Lambda developmentUnderstanding of agent tool integration patterns, including function calling, tool schema definition, and parameter validationNice to haveFamiliarity with MCP protocol implementation (server or client)Knowledge of LangChain / LangGraph tool integrationBackground in AWS Bedrock AgentCore Gateway target registrationSkills in semantic tool indexing, including embedding generation for tool descriptionsExperience with agent framework integration (Strands, Crew, AutoGPT)We offerWe gather like-minded people:Top tech minds driving innovation in AI, cloud and digital platform modernizationSupportive team and agile, startup-like cultureHybrid by design mode and opportunity to work remotely within PolandChance to work abroad for up to 60 days annuallyBusiness-driven relocation opportunitiesWe provide growth opportunities:Career development programsThought leadership, mentoring, soft skills and well-being programsCertification (Anthropic, Gemini, GCP, Azure, AWS)English classesWe cover it all:Stable payParticipation in the Employee Stock Purchase Plan with a 15% discountBenefits package (health insurance, multisport, shopping vouchers)Referral bonuses up to $2,000Offices featuring entertainment and relaxation zones, table tennis and football, free snacks, coffee and moreCorporate, social and well-being eventsPlease, note:Benefits listed above are available to employees onlyWe are open for working with Contractors. Terms of B2B cooperation agreements are agreed individuallyWe will reach out to selected candidates exclusivelyEPAM is global leader in AI transformation engineering and integrated consulting, serving Forbes Global 2000 companies and ambitious startups. With over thirty years of expertise in custom software, product and platform engineering, we empower our clients to become AI-Native enterprises, driving measurable value from innovation and digital investments.