Full-Stack Software Engineering Manager

EPAM Systems Inc; United States; Remote; USD 180,000 - 230,000; Full time

Job summary

EPAM Systems seeks a Full-Stack Software Engineering Manager to build GenAI-enabled web experiences and frontend integration libraries for enterprise use.

You will develop scalable UIs, reusable components, and client-side integrations for LLM features, collaborating with product and design on conversational UX patterns while ensuring security, accessibility, and robust testing across client-side and full-stack work.

Qualifications

• 8+ years of experience in full-stack software engineering.
• Proven experience building production applications with React, TypeScript, or Vue for enterprise use cases.
• Experience integrating GenAI capabilities and LLM APIs into web apps.

Responsibilities

• Architect end-to-end GenAI-powered web apps and UI integrations.
• Design responsive, accessible UIs optimized for streaming and low latency.
• Build a reusable frontend component library and design systems for enterprise GenAI apps.
• Implement LLM-based experiences using LangChain or LlamaIndex with OpenAI/Claude/Gemini.
• Collaborate with product and design to iterate on AI UX patterns including chat assistants.

Skills

Frontend UIs

React

TypeScript

Vue

GenAI

LLM APIs

REST APIs

Frontend Architecture

Tools

Docker

AWS

LangChain

LlamaIndex

OpenAI API

Job description

We are looking for a Full-Stack Software Engineering Manager to create intuitive, high-speed web experiences and frontend integration libraries for GenAI and automation. In this role, you will develop enterprise-ready UIs, reusable components, and client-side integrations for LLM features across internal teams while collaborating with product and design on conversational UX patterns.

Responsibilities

• Architect and ship end-to-end GenAI-powered applications, focusing on intuitive web-based UIs and high-performing client-side API integrations.
• Design responsive, accessible frontend experiences fine-tuned for streaming responses and low latency.
• Build and sustain a reusable library of frontend components, hooks, and design systems for enterprise-grade GenAI applications.
• Implement LLM-based experiences leveraging frameworks such as LangChain or LlamaIndex paired with OpenAI, Claude, or Gemini.
• Partner with designers and product managers to quickly iterate on AI UX patterns, including chat assistants, prompt builders, and feedback loops.
• Guarantee security, accessibility, observability, and thorough test coverage across client-side and full-stack work.
• Craft responsive, accessible, high-performance web UIs tailored to AI interactions such as streaming text, prompt inputs, citations, and summaries.
• Manage a shared library of reusable frontend components and hooks so internal teams can embed GenAI capabilities into their applications.
• Develop UI components that deliver transparency, observability, and trust in AI-generated outputs.

Requirements

• 8+ years of experience in full-stack software engineering spanning frontend UIs, REST APIs, and microservices.
• Proven experience building production applications with React, TypeScript, or Vue for enterprise use cases.
• Skills in integrating GenAI capabilities, LLM APIs, and prompt UI patterns into web-based applications.
• Proficiency in Python backend development, plus 4+ years of experience building and consuming cloud microservices on AWS, Docker, and REST APIs.
• Showcase of creating, documenting, and maintaining reusable component libraries, design systems, and custom hooks.
• English proficiency at a B2+ level or higher.

Nice to have

• Familiarity with real-time streaming UX patterns, such as SSE/WebSockets, prompt builders, citations, and summary UI components.
• Understanding of WCAG 2.1 AA compliance and approaches to architecting accessible UI components.
• Knowledge of client-side or Node.js LangChain, LangGraph, or LlamaIndex orchestration.

Qualifications

• Qualifications in RAG pipelines, vector search platforms like Pinecone or OpenSearch, and embedding fundamentals.
• Capability to work with AI evaluation tools, feedback loop design, and interface-level guardrails.