ai engineer for conversational AI

EPAM offers enterprise software products, open-source solutions, and accelerators.

• Architect and develop a conversational AI/agentic application on Databricks using LangChain and/or LangGraph;
• Build semantic search and RAG pipelines using vector embeddings and a vector database;
• Establish and refine similarity-matching logic, including embedding model selection, distance metrics, thresholds, and ranking of match results;
• Connect to data sources, including Databricks Unity Catalog tables, Delta Lake, and APIs, to build and prepare the knowledge base;
• Manage the complete ML/LLMOps lifecycle, including experimentation, evaluation, versioning, deployment, and production monitoring;
• Partner with business stakeholders to translate use cases into technical specifications;
• Produce clean, documented, maintainable Python code and set up testing and CI/CD workflows;
• Ensure data privacy, access control, and oversight of token usage and compute costs.

• At least 3 years of software/ML engineering experience, including at least 1 year working with LLM-based applications;
• Strong Python skills, including building, debugging, and refactoring production-level code;
• Deep knowledge of LangChain and/or LangGraph, including agent design, chains, tool calling, and state/memory handling;
• Hands-on experience with vector databases, embeddings, semantic search, and RAG retrieval systems;
• Working knowledge of Databricks, including notebooks, jobs, clusters, and Unity Catalog;
• Practical experience integrating and prompt-engineering with LLM providers such as OpenAI, Anthropic, and Azure OpenAI;
• A Bachelor's degree in Computer Science, Data Science, Engineering, or a related discipline, or equivalent hands-on experience;
• Strong communication skills and ability to navigate ambiguous requirements with minimal documentation;
• English proficiency at B2 level or above;
• Nice to have: experience with MLOps/LLMOps tools such as MLflow, model/prompt versioning, and LLM output evaluation frameworks; API/backend development with FastAPI or Flask; front-end/chat interface integration.

• Remote work from Ukraine.