[Hiring] Lead GenAI Engineer @EPAM

Role Description

We're currently seeking a Lead GenAI Engineer to become part of our team. The initiative centers on building an advanced user interface powered by the Saffron UI framework, designed to elevate the user experience through tight integration with backend systems and APIs. The aim is to hit ambitious milestones while remaining flexible as project scope and timelines continue to shift. This position centers on constructing and advancing GenAI-driven application features, spanning LLM integrations, MCP-based tooling, and agentic workflow design. The engineer will work across the entire application stack, building AI-powered backend services and interfaces that enable streaming interactions, tool execution, structured outputs, and human-in-the-loop processes.

• Engage across the entire feature development cycle, spanning initial ideation through launch and continued maintenance.
• Convert business and product needs into clearly structured technical implementations.
• Develop and sustain intuitive, responsive interfaces that provide users with a seamless experience.
• Create and maintain backend services that drive essential application capabilities.
• Coordinate closely with designers, product owners, and engineering peers to influence product direction.
• Identify and fix issues impacting application speed, reliability, and overall usability.
• Contribute to code review processes to uphold consistent quality standards across the codebase.
• Record technical decisions, process flows, and system behavior to facilitate team-wide knowledge transfer.
• Provide estimates for task scope and timelines while keeping stakeholders informed of progress.
• Track emerging tools and methods, suggesting enhancements to current development practices.

Qualifications

• At least five years of hands-on, applicable professional background.
• A minimum of one year spent leading or managing engineering teams.
• Direct experience developing applications built on LLM providers such as Claude, OpenAI, or comparable platforms.
• Applied experience with Model Context Protocol (MCP), covering tool schema design and building or adapting MCP servers.
• Background architecting multi-step agentic workflows, including tool usage, orchestration mechanisms, and safety controls.
• Robust full-stack expertise spanning React and TypeScript for frontend work along with Python/FastAPI or Node.js for backend development.
• Experience connecting LLM provider APIs, covering streaming output handling, function/tool calling, and structured response formats.
• Effective communication ability with working English fluency at B2 level or higher, supporting clear interpretation of business needs and their conversion into agentic system designs.

Nice to have

• Background designing and building Retrieval-Augmented Generation (RAG) pipelines, including chunking approaches and retrieval techniques.
• Exposure to vector database solutions such as Pinecone, Weaviate, or pgvector for embedding storage and retrieval.
• Experience developing AI-native interface patterns, including streaming output displays, tool-call visualizations, and human-in-the-loop states.
• Familiarity with eval-driven development practices using BrainTrust or similar evaluation tools and frameworks.
• Experience overseeing prompt version control and running regression tests against established evaluation benchmarks.