We’re looking for a Machine Learning Engineer to join EPAM in London, United Kingdom, in a hybrid working mode. You will contribute to an enterprise AI program for one of our clients by building and surfacing MCP Servers and Tools via the internal MCP Gateway and implementing evaluation mechanisms for large language models and agent-based systems. This is a highly technical role combining backend engineering, AI architecture, and enterprise integration to deliver scalable AI solutions.
As an AI Engineer, you will work on intelligent enterprise enablement through Model Context Protocol (MCP) integrations and advanced agent frameworks. The role involves API development with FastAPI, deployment of containerized systems, and implementing large language model (LLM) strategies such as prompt engineering and RAG (Retrieval-Augmented Generation). The successful candidate will operate in a Classic Agile environment to design, develop, and optimize next-generation enterprise AI capabilities.
Responsibilities
- Build and surface MCP Servers and Tools using the internal MCP Gateway
- Develop APIs and service endpoints with FastAPI for MCP integrations
- Implement agent and LLM frameworks (e.g., LangChain, LangGraph) to enable sophisticated AI workflows
- Apply prompt engineering strategies and build RAG-based architecture for enhanced response accuracy
- Automate quality controls and develop evaluation systems for LLM reliability and performance
- Containerize and orchestrate AI services using Kubernetes for scalable deployment
- Collaborate cross-functionally with product, QA, and architecture teams to ensure secure, enterprise-grade solutions
- Maintain documentation for MCP integrations, testing pipelines, and workflow standards
- Integrate CI/CD practices to streamline deployment and testing processes
Requirements
- Strong programming experience in Python for backend development and automation
- Expertise in REST API development using FastAPI for production-scale services
- Familiarity with Model Context Protocol (MCP) standards, server/client patterns
- Working knowledge of LLM/agent frameworks such as LangChain or LangGraph
- Understanding of containerization and orchestration tools like Kubernetes
- Ability to implement prompt engineering principles and RAG-based solutions
- Solid grasp of Agile delivery models, CI/CD workflows, and secure coding practices
- Excellent problem-solving and cross-team communication skills
Nice to have
- Experience with observability and monitoring tools for AI-driven workloads
- Familiarity with vector databases for semantic search and retrieval
- Knowledge of cloud platforms (AWS, GCP, Azure) and GPU-accelerated compute
- Background designing evaluation frameworks for AI model performance
- Exposure to large-scale AI deployment in enterprise environments
We offer
- EPAM Employee Stock Purchase Plan (ESPP)
- Protection benefits including life assurance, income protection and critical illness cover
- Private medical insurance and dental care
- Employee Assistance Program
- Cyclescheme, Techscheme and season ticket loans
- Various perks such as free Wednesday lunch in-office, on-site massages and regular social events
- Learning and development opportunities including in-house training and coaching, professional certifications, and courses
- If otherwise eligible, participation in the discretionary annual bonus program
- If otherwise eligible and hired into a qualifying level, participation in the discretionary Long-Term Incentive (LTI) Program
#J-18808-Ljbffr…