[Hiring] Senior GenAI Engineer @EPAM

Role Description

We're looking for a Senior GenAI Engineer to join our team. The project involves the development of a sophisticated user interface utilizing the Saffron UI framework, aimed at enhancing user experience through seamless integration with backend services and APIs. The goal is to meet ambitious targets while adapting to evolving project requirements and deadlines. The role will focus on building and evolving GenAI-powered application capabilities, including LLM integrations, MCP-based tooling, and agentic workflows. The engineer will contribute across the full application stack, developing AI-enabled backend services and user experiences that support streaming interactions, tool execution, structured outputs, and human-in-the-loop workflows.

• Take part in the full lifecycle of feature development, from initial concept through deployment and ongoing support
• Translate business and product requirements into well-structured technical solutions
• Build and maintain intuitive, responsive user interfaces that deliver a smooth end-user experience
• Develop and maintain backend services that power core application functionality
• Work closely with designers, product managers, and fellow engineers to shape product direction
• Troubleshoot and resolve issues affecting application performance, stability, and usability
• Take part in code reviews to maintain high standards of quality and consistency across the codebase
• Document technical decisions, workflows, and system behavior to support team knowledge sharing
• Estimate effort and timelines for assigned tasks and communicate progress to stakeholders
• Stay current with emerging tools and approaches, recommending improvements to existing practices

Qualifications

• A minimum of three years of hands-on, relevant professional experience
• Practical experience building applications powered by LLM providers such as Claude, OpenAI, or similar platforms
• Hands-on experience with Model Context Protocol (MCP), including designing tool schemas and building or modifying MCP servers
• Experience designing multi-step agentic workflows, encompassing tool use, orchestration logic, and safety guardrails
• Strong full-stack development background, combining React and TypeScript on the frontend with Python/FastAPI or Node.js on the backend
• Experience integrating LLM provider APIs, including handling streaming responses, function/tool calling, and structured output formats
• Solid communication skills with working English fluency at B2 level or above, enabling clear understanding of business requirements and their translation into agentic architectures

Requirements

• Experience designing and implementing Retrieval-Augmented Generation (RAG) pipelines, including retrieval methods and chunking strategies
• Familiarity with vector database technologies such as Pinecone, Weaviate, or pgvector for storing and retrieving embeddings
• Experience building AI-native UI patterns, including streaming response displays, tool-call visualization, and human-in-the-loop interaction states
• Background in eval-driven development using BrainTrust or comparable evaluation frameworks and tooling
• Experience managing prompt versioning and conducting regression testing against defined evaluation sets