We are seeking a GenAI Engineer to lead the end-to-end development, deployment and operation of enterprise-grade AI-powered applications. The role combines backend engineering, LLM integration, cloud infrastructure and AI platform operations to deliver scalable GenAI solutions in production environments. You will work closely with AI/DS, Product and DevOps teams to build and scale AI-driven applications, ensuring reliability, observability, performance optimization and operational excellence across the full AI SDLC. The role also includes contributing to GenAI-assisted development practices, scaling enterprise AI SDLC processes, supporting AI Beauty Chat initiatives through agentic micro-pod delivery models and performing System Steward responsibilities across AI platform initiatives.
Responsibilities
-
Design, develop, deploy and maintain backend services for AI/LLM-powered applications
-
Own E2E delivery of GenAI features from implementation to production support
-
Integration and operation of LLM APIs (e.g. OpenAI) in enterprise production environments
-
Development of APIs, orchestration layers and microservices supporting agentic AI workflows
-
Optimization of LLM systems for latency, resiliency, retries, fallbacks and cost efficiency
-
Implementation of CI/CD pipelines, observability, monitoring and logging for AI services
-
Collaboration with AI/DS, Product, DevOps and platform teams to streamline delivery and improve reliability
-
Work with Azure cloud environments and distributed systems (Redis, Kafka, SQL/NoSQL)
-
Support for MCP integrations, agentic memory initiatives and AI orchestration frameworks
-
Drive GenAI-assisted development practices and scale AI SDLC processes
-
Contribution to AI Beauty Chat delivery through agentic micro-pod execution models
-
Execution of System Steward responsibilities in agentic micro-pods
Requirements
-
2+ years of Python backend engineering experience
-
Expertise in building and operating production-grade GenAI/LLM applications end-to-end
-
Hands-on experience with OpenAI or other LLM APIs in production
-
Proficiency in prompt engineering, agentic workflows and orchestration patterns
-
Capability to handle LLM operational challenges: latency, retries, fallbacks, observability and cost optimization
-
Strong understanding of scalable backend and distributed system architecture
-
Skills in CI/CD, DevOps workflows and Azure cloud environments
-
Background in applying GenAI across the SDLC (AI-assisted development, testing, deployment and delivery workflows)
-
Working knowledge of SQL/NoSQL databases, Redis and Kafka
-
Familiarity with Databricks and MCP
-
Excellent English communication skills (B2+ level)
We offer
-
International projects with top brands
-
Work with global teams of highly skilled, diverse peers
-
Healthcare benefits
-
Employee financial programs
-
Paid time off and sick leave
-
Upskilling, reskilling and certification courses
-
Unlimited access to the LinkedIn Learning library and 22,000+ courses
-
Global career opportunities
-
Volunteer and community involvement opportunities
-
EPAM Employee Groups
-
Award-winning culture recognized by Glassdoor, Newsweek and LinkedIn
