We are seeking a Lead GenAI Engineer to own end-to-end delivery, deployment, and operations of enterprise AI-powered applications at scale. You will combine Python backend engineering, LLM integrations, and Azure DevOps practices to ship reliable GenAI features with strong observability and performance. You will partner with AI/DS, Product, and DevOps to improve the full AI SDLC—apply now.
Responsibilities
-
Design, build, deploy, and sustain backend services for AI/LLM-powered applications
-
Lead E2E delivery of GenAI features from implementation through production support
-
Integrate and run LLM APIs within enterprise production environments
-
Create APIs, orchestration layers, and microservices that enable agentic AI workflows
-
Tune LLM systems for latency, resilience, retries, fallbacks, and cost efficiency
-
Set up CI/CD pipelines, observability, monitoring, and logging for AI services
-
Partner with AI/DS, Product, DevOps, and platform teams to streamline delivery and raise reliability
-
Support MCP integrations, agentic memory initiatives, and AI orchestration frameworks
-
Champion GenAI-assisted development practices and expand AI SDLC processes
-
Contribute to AI Beauty Chat delivery through agentic micro-pod execution models
-
Execute System Steward responsibilities in agentic micro-pods
Requirements
-
Proven experience in Python backend engineering with 5+ years of professional experience
-
Hands-on experience building and operating production-grade GenAI/LLM applications end-to-end
-
Practical expertise with OpenAI or other LLM APIs in production environments
-
Strong capability in prompt engineering, agentic workflows, and orchestration patterns
-
Demonstrated ability to address LLM operational challenges, including latency, retries, fallbacks, observability, and cost optimization
-
Solid understanding of scalable backend and distributed system architecture
-
Hands-on experience with CI/CD, DevOps workflows, and Azure cloud environments
-
Working knowledge of applying GenAI across the SDLC, including AI-assisted development, testing, deployment, and delivery workflows
-
Practical 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
