Lead GenAI Engineer

EPAM Systems; Brasil; Remote; BRL 250,000 - 360,000; Full time

Benefits offered by this job

Healthcare benefits

Paid time off

Upskilling and certification

LinkedIn Learning access

Job summary

EPAM Systems, Inc. is seeking a Lead GenAI Engineer to drive the full lifecycle of enterprise AI-powered apps. You will lead backend services, integrate LLM APIs, and ensure scalable, observable, and cost-efficient GenAI solutions in production.

Collaboration with AI/DS, Product, and DevOps teams is essential to success. You will optimize latency, reliability, and scale across Azure-based cloud environments and distributed systems such as Redis and Kafka, while championing best practices for AI

Qualifications

• 5+ years in AI engineering or backend development.
• Experience delivering GenAI/LLM apps to production.
• Strong knowledge of OpenAI or similar APIs.
• Proven ability to improve latency, reliability, and cost control.

Responsibilities

• Design, construct, deploy, and maintain backend services powering AI/LLM apps.
• Own GenAI feature delivery from build to production support.
• Connect and manage LLM APIs within enterprise production environments.
• Develop APIs, orchestration layers, and microservices for agentic AI workflows.
• Tune LLM systems for latency, resiliency, retries, fallbacks, and cost efficiency.
• Set up CI/CD, observability, monitoring and logging for AI services.
• Collaborate with AI/DS, Product, DevOps and platform teams to boost reliability.
• Operate within Azure and distributed systems (Redis, Kafka, SQL/NoSQL).
• Facilitate MCP integrations and agentic memory initiatives.
• Advocate GenAI-assisted development and scale the AI SDLC.
• Assist AI Beauty Chat delivery via agentic micro-pod execution models.

Skills

Python backend

LLM integration

OpenAI API

Azure cloud

Distributed systems

CI/CD

Observability

English proficiency

Leadership experience

Tools

Redis

Kafka

Databricks

SQL/NoSQL databases

MCP

Job description

We are on the lookout for a Lead GenAI Engineer to join our team. In this role, you will oversee the full development, deployment, and operational cycle of enterprise-grade AI-powered applications. The position merges backend engineering, LLM integration, cloud infrastructure, and AI platform operations to deliver scalable GenAI solutions in live production environments. You will collaborate closely with AI/DS, Product, and DevOps teams to build and grow AI-driven applications, upholding reliability, observability, performance optimization, and operational excellence across the complete AI SDLC. The role also involves supporting GenAI-assisted development practices, helping expand the client's enterprise AI SDLC processes, contributing to AI Beauty Chat initiatives through agentic micro-pod delivery models, and carrying out System Steward duties across AI platform initiatives.ResponsibilitiesDesign, construct, deploy, and maintain backend services that power AI/LLM-driven applicationsHold full accountability for GenAI feature delivery, from initial build through to production supportConnect and manage LLM APIs, including OpenAI, within enterprise production environmentsDevelop APIs, orchestration layers, and microservices that enable agentic AI workflowsTune LLM systems for latency, resiliency, retries, fallbacks, and cost efficiencySet up CI/CD pipelines, observability, monitoring, and logging for AI servicesWork alongside AI/DS, Product, DevOps, and platform teams to simplify delivery and boost reliabilityOperate within Azure cloud environments alongside distributed systems, including Redis, Kafka, and SQL/NoSQL databasesFacilitate MCP integrations, agentic memory initiatives, and AI orchestration frameworksAdvocate for GenAI-assisted development practices and support scaling of the client's AI SDLC processesAssist with AI Beauty Chat delivery through agentic micro-pod execution modelsCarry out System Steward duties within agentic micro-podsRequirementsA minimum of 5 years of experience in a relevant fieldAt least one year of experience in a team leadership or management capacityMain area of specialization in AI Engineering, with an emphasis on backend systemsWell-developed background in Python backend developmentTrack record of building and running enterprise-grade GenAI/LLM applications from start to finishDirect experience working with OpenAI or other LLM APIs in live production settingsCompetence in prompt engineering and various orchestration approachesExperience tackling operational hurdles tied to LLMs, including latency, retry logic, fallback handling, observability, and cost controlDeep familiarity with distributed systems and scalable backend architectureBackground in CI/CD practices, DevOps tooling, and Azure-based cloud environmentsExperience embedding GenAI into the software development lifecycle, spanning AI-assisted coding, testing, deployment, and release processesPractical knowledge of SQL/NoSQL databases, along with Redis and KafkaStrong ability to communicate effectively with varied audiencesExcellent English proficiency (B2 level or higher)Nice to haveExposure to agentic workflow designHands-on background with Databricks and MCPWe offerInternational projects with top brandsWork with global teams of highly skilled, diverse peersHealthcare benefitsEmployee financial programsPaid time off and sick leaveUpskilling, reskilling and certification coursesUnlimited access to the LinkedIn Learning library and 22,000+ coursesGlobal career opportunitiesVolunteer and community involvement opportunitiesEPAM Employee GroupsAward-winning culture recognized by Glassdoor, Newsweek and LinkedInEPAM 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.