ai engineer

EPAM provides digital platform engineering and software product development services, focusing on enterprise-grade AI solutions, agentic workflows, and RAG-based systems.

• Own the end-to-end architecture of GenAI platforms across multiple services and teams, defining standards, patterns, and reference implementations;
• Lead the design of agent orchestration in LangGraph / LangChain or equivalent, and set best practices for the team;
• Architect production RAG end-to-end, including chunking, embeddings, vector stores, hybrid retrieval, reranking, caching, and grounded synthesis;
• Drive the design and delivery of Python / FastAPI services, establishing service templates and conventions;
• Define the observability and evaluation strategy for accuracy, cost, and regression across the platform;
• Own the deployment platform on Docker and Kubernetes with CI/CD, test, eval, and canary gates;
• Lead LLM cost engineering strategy, including model routing, prompt optimization, caching, and token accounting;
• Establish GenAI safety and governance practices, including hallucination control, prompt-injection defense, and PII handling;
• Partner with data engineering leadership on semantic layers and pipelines, and align roadmaps across teams;
• Mentor and grow senior and mid-level engineers through design reviews, pairing, and technical coaching;
• Conduct hiring and technical interviews;
• Represent engineering in conversations with clients, product, and executive stakeholders.

• 6+ Years in software engineering, with 3+ years shipping production LLM / agentic systems;
• 1+ Years of experience leading engineers or technical workstreams;
• Proven track record of owning architecture for multi-service GenAI or distributed systems in production;
• Expert-level proficiency in Python and FastAPI;
• Deep production expertise in LangChain and LangGraph or equivalent stacks;
• Strong background in production RAG, including embeddings, chunking, and hybrid retrieval;
• Advanced skills in vector databases such as Pinecone, Weaviate, pgvector, OpenSearch, or Databricks Vector Search;
• Hands-on production experience with at least one major LLM provider such as AWS Bedrock, OpenAI / Azure OpenAI, or Anthropic;
• Strong competency in Kubernetes and Docker in production environments;
• Deep expertise in cloud engineering on AWS;
• Solid command of observability and tracing tools, evaluation harnesses, and latency/cost ownership;
• Experience designing and owning CI/CD for AI systems;
• Demonstrated experience mentoring engineers and leading design reviews;
• Strong written and spoken English (B2+ level);
• Nice to have: Databricks depth (MLflow, Vector Search, Unity Catalog, PySpark/SQL), experience with LLM fine-tuning (PEFT, LoRA, QLoRA), understanding of MCP servers and tool integration, expertise in GenAI governance and FinOps, background in classical ML / DL (NLP, BERT-family, time-series, CV).

• Remote work opportunity.