Lead GenAI Engineer: End-to-End AI Systems & Observability

EPAM Systems Inc; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

EPAM Systems is seeking a Lead AI Agentic Developer to drive AI-powered engineering initiatives spanning backend Python/FastAPI, frontend React/TypeScript, and Google Vertex AI.

You will own GenAI systems end-to-end, ensuring observability, cost controls, and collaboration with AI coding assistants to accelerate delivery. The role requires a strong foundation in software development and cloud tooling.

Qualifications

• 5+ years of software development experience with hands-on GenAI and agentic development including AI coding assistants like Claude Code and GitHub Copilot
• Deep expertise in GenAI design patterns and GenAI cloud platforms including Vertex AI
• Hands-on experience with LLM observability and tracing using LangFuse, LangSmith, or similar platforms
• Strong skills in prompt-engineering methods and structured outputs
• Solid understanding of LLM orchestration, RAG, multi-agent systems, tool calling, and agent evaluation
• Proficiency in Python, FastAPI, asynchronous programming, Pydantic, and SQLAlchemy
• Experience with Docker, Kubernetes, and modern CI/CD
• Knowledge of authentication/authorization patterns (OAuth 2.0, JWT, RBAC)
• Frontend experience with React/TypeScript and data-visualization basics

Responsibilities

• Design, build, deploy, and support AI-powered apps using Python/FastAPI backends, React/TypeScript frontends, and Vertex AI
• Own GenAI systems end-to-end including architecture choices, feature delivery, operational readiness, and cost optimization
• Collaborate with AI coding assistants to speed delivery and improve code quality
• Create technical design specifications aligned with standards and business needs
• Implement LLM orchestration, RAG, multi-agent workflows, and structured-output generation
• Create observability pipelines with trace analysis, token usage, and cost metrics
• Provide technical leadership and mentorship in agentic development and AI-tool integration
• Evaluate cross-platform trade-offs for architecture consistency and optimization
• Troubleshoot defects, perform root-cause analysis, and deliver full-stack enhancements
• Communicate risks and blockers early to protect commitments
• Coordinate multiple deliverables and resolve production issues efficiently
• Monitor dashboards and AI-model performance using LangFuse, Grafana, Dynatrace, Splunk

Skills

Generative AI

Agentic development

Python

FastAPI

React

TypeScript

LLM observability

Docker

Kubernetes

SQLAlchemy ORM

OAuth 2.0

JWT

RBAC

Vertex AI

BigQuery

GitHub Actions

ArgoCD

LangFuse

Grafana

Dynatrace

Splunk

CI/CD

Tools

LangSmith

Grafana

Dynatrace

Splunk

Vertex AI

BigQuery

Job description

EPAM Systems is seeking a Lead AI Agentic Developer to drive AI-powered engineering initiatives spanning backend Python/FastAPI, frontend React/TypeScript, and Google Vertex AI.

You will own GenAI systems end-to-end, ensuring observability, cost controls, and collaboration with AI coding assistants to accelerate delivery. The role requires a strong foundation in software development and cloud tooling.