Senior AI Engineer - Conversational AI & Semantic Search (Databricks / LangChain)

We are looking for a Senior AI Engineer to architect, develop, and launch an AI-driven chatbot/agent on Databricks, following a design similar to an existing internal tool (LangGraph/LangChain orchestration combined with vector database semantic search), but tailored to a new business scenario. The right candidate will be able to operate autonomously, infer and adapt concepts from previous builds, and take full ownership of the project from initial prototype to full production release.

Responsibilities

• Architect and develop a conversational AI/agentic application leveraging LangChain and/or LangGraph, hosted on Databricks
• Build semantic search and retrieval-augmented generation (RAG) pipelines using vector embeddings paired with a vector database (such as Databricks Vector Search, Chroma, Pinecone, or FAISS)
• Establish and refine similarity-matching logic, including embedding model selection, distance metrics, thresholds, and ranking of "% match" results
• Connect to various data sources (Databricks Unity Catalog tables, Delta Lake, APIs) to build and prepare the knowledge base/corpus
• Manage the complete ML/LLMOps lifecycle, covering experimentation, evaluation, versioning, deployment, and production monitoring of the chatbot
• Partner with business stakeholders to convert new use cases into clear technical specifications
• Produce clean, well-documented, maintainable Python code while setting up testing and CI/CD workflows for the application
• Guarantee proper data privacy practices, access control, and cost oversight (covering token usage and compute resources)

Requirements

• A minimum of 3 years in software/ML engineering, including at least 1 year working with LLM-based applications
• Strong Python skills, covering the ability to build, debug, and refactor production-level code
• Deep knowledge of LLM orchestration frameworks like LangChain and/or LangGraph, encompassing agent design, chains, tool calling, and state/memory handling
• Hands-on experience with vector databases, embeddings, and semantic search, including generating embeddings, indexing within a vector store, and building similarity search or RAG retrieval systems
• Working knowledge of the Databricks platform, 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)
• Excellent communication abilities, capable of navigating ambiguous requirements with minimal documentation support
• English language skills at B2 level or above

Nice to have

• Exposure to MLOps/LLMOps tools such as MLflow, along with model/prompt versioning and LLM output evaluation frameworks
• Experience in API/backend development using frameworks like FastAPI or Flask to deploy the chatbot as a service
• Understanding of front-end/chat interface integration, connecting a backend agent to a chat UI

Benefits

With us you can:

• Work on a flexible schedule remotely or from any of our comfortable offices or coworking spaces in Ukraine
• Receive the necessary equipment to perform your work tasks
• Change projects and technology stacks within EPAM
• Gain experience in various business domains (Insurance, E-commerce, Healthcare, Finance, Travelling, Media, Artificial Intelligence, and more)
• Relocation opportunities may be available for eligible candidates, depending on the role and openings at other EPAM locations
• Participate in volunteer, charity programs and communities (both technical and interest-based)

We focus on your professional growth:

• You can plan your individual career path together with your manager
• Receive regular feedback from colleagues
• Improve your English for free with certified teachers (Speaking Clubs, client interview preparation courses, etc.)
• Get the opportunity to undergo free training and certification in AWS, GCP, or Azure Clouds
• Use the internal E-learn training program (18,200+ specialized training and mentoring programs)
• Access corporate accounts on LinkedIn Learning, Get Abstract and other partner resources
• Study at EPAM Solution Architecture School with the instructors who are practicing architects
• Develop as a leader, join Delivery Management, Resource Management, Leadership Essentials school and more
• Participate in internal communities (500+ meetups, technical discussions, brainstorming sessions, online events and conferences annually)

What we offer:

• Vacation and sick leave (including a sick leave without a medical certificate)
• A wide range of Voluntary Medical Insurance programs providing both medical treatment and various preventive options (including sports activities)
• Medical insurance for family members at corporate rates
• Company support during significant life events (childbirth or adoption, marriage, etc.)
• Support for psychological comfort: discounts on services from mental health specialists or coaches, thematic training
• E-kids program - a free programming language training program for EPAMers' children