We are searching for a Senior nAI Engineer to become part of our team. This role puts you in charge of the entire development, deployment, and operational journey of enterprise-grade AI-powered applications. It draws together backend engineering, LLM integration, cloud infrastructure, and AI platform operations to bring scalable GenAI solutions into live production settings. You will team up with AI/DS, Product, and DevOps groups to construct and expand AI-driven applications, safeguarding reliability, observability, performance optimization, and operational excellence throughout the entire AI SDLC. This position further includes backing GenAI-assisted development approaches, aiding in the growth of the client's enterprise AI SDLC processes, participating in AI Beauty Chat initiatives via agentic micro-pod delivery models, and handling System Steward obligations across AI platform efforts.
Responsibilities
-
Craft, build, launch, and support backend services that drive AI/LLM-powered applications
-
Assume complete responsibility for GenAI feature delivery, starting from initial development all the way to production support
-
Link and administer LLM APIs, such as OpenAI, inside enterprise production settings
-
Build out APIs, orchestration layers, and microservices to power agentic AI workflows
-
Adjust LLM systems to improve latency, resiliency, retry handling, fallback logic, and cost management
-
Configure CI/CD pipelines along with observability, monitoring, and logging capabilities for AI services
-
Team up with AI/DS, Product, DevOps, and platform groups to ease delivery and reinforce reliability
-
Function within Azure cloud settings and distributed systems, spanning Redis, Kafka, and SQL/NoSQL databases
-
Support MCP integrations, agentic memory efforts, and AI orchestration frameworks
-
Promote GenAI-assisted development approaches and contribute to scaling the client's AI SDLC processes
-
Play a role in AI Beauty Chat delivery through agentic micro-pod execution models
-
Handle System Steward obligations within agentic micro-pods
Requirements
-
At least 3 years of experience relevant to this role
-
Primary specialization in AI Engineering with an emphasis on backend systems
-
Strong background in Python for backend engineering
-
Proven experience delivering and running production-grade GenAI/LLM applications from end to end
-
Direct, hands-on work with OpenAI or comparable LLM APIs within production contexts
-
Proficiency in prompt engineering along with various orchestration techniques
-
Experience tackling operational issues tied to LLMs, covering latency, retries, fallback strategies, observability, and cost efficiency
-
Firm grasp of distributed system design and scalable backend architecture
-
Background in CI/CD practices, DevOps processes, and Azure cloud platforms
-
Experience weaving GenAI into the SDLC, including AI-assisted coding, testing, deployment, and release workflows
-
Practical familiarity with SQL/NoSQL databases, Redis, and Kafka
-
Strong ability to communicate clearly and effectively
-
Excellent English proficiency (B2 level or higher)
Nice to have
-
Background working with agentic workflow patterns
-
Practical exposure to Databricks and MCP
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
EPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.
