Lead Java Engineer - AI Native

EPAM Systems; India; On-site; INR 2,000,000 - 3,000,000; Full time

Job summary

EPAM Systems is looking for a Lead Java Engineer – AI Native in India to design and build complex production systems while promoting AI-native engineering practices across a team. Responsibilities involve developing scalable Java applications using Spring Boot, deploying Model Context Protocol servers, and integrating with enterprise tools.

The ideal candidate will have 8–12 years of experience, proven leadership in technical projects, and proficiency with AI coding assistants and cloud-native engineering.

Qualifications

• 8–12 years of professional Java development with complex systems ownership.
• Deep expertise in Spring Boot, Spring Cloud, and microservices patterns.
• Experience leading technical teams through architecture governance.

Responsibilities

• Design and maintain scalable Java applications with a high degree of autonomy.
• Build and deploy Java services for LLM-based agents.
• Conduct architecture reviews and mentor junior engineers.

Skills

Java development

Spring Boot

Microservices architecture

Cloud engineering

AI coding assistants

Tools

GitHub Copilot

AWS

Azure

Jira

Confluence

Job description

We are seeking a Lead Java Engineer – AI Native to design, build and own complex production systems while championing AI‑native engineering practices across a team.

Responsibilities

• Design, develop and maintain scalable Java applications using Spring Boot and microservices architecture, owning features end‑to‑end with a high degree of autonomy.
• Build and deploy Model Context Protocol (MCP) servers that expose Java services, databases or internal tools to LLM‑based agents — enabling agents to act on live enterprise data and systems.
• Implement end‑to‑end agentic SDLC pipelines: automated specification drafting, AI‑driven code generation, intelligent test creation, CI/CD integration and deployment validation orchestrated by AI agents.
• Integrate agentic pipelines with enterprise tools and platforms (Jira, Confluence, GitHub, ServiceNow, observability stacks) via MCP connectors or REST/event‑driven APIs.
• Use AI coding assistants (GitHub Copilot, Cursor, Claude Code or equivalent) and frontier LLMs (Claude, GPT‑4o, Gemini) across the full development lifecycle every day, critically evaluating AI outputs for correctness, security and edge cases before committing.
• Bring an AI‑first mindset to automate repetitive engineering tasks, measure outcomes rather than activity and identify AI‑leverage opportunities within your delivery area.
• Contribute to the team’s shared library of prompt templates, reusable agent patterns and MCP connectors.
• Conduct code and architecture reviews, mentor Junior and Mid‑level engineers in Java best practices and AI‑native engineering methods.
• Maintain strong automated test coverage (unit, integration, contract, AI‑generated) and healthy CI/CD pipeline practices.
• Track frontier developments — new model releases (Claude, GPT, Gemini, Llama), emerging agent frameworks, new MCP connectors — and bring relevant changes back to the team within weeks.

Requirements

• 8–12 years of professional Java development with clear ownership of complex production systems.
• Deep expertise in Spring Boot, Spring Cloud and Spring Data, plus Spring Security and microservices design patterns.
• Strong architectural skills across distributed systems, event‑driven architecture and domain‑driven design (DDD), including CQRS/ES.
• Cloud‑native engineering on AWS, GCP or Azure — IaC, serverless patterns, managed services and cloud‑native observability.
• Proven experience leading technical teams through architecture governance, coding standards and mentoring and technical onboarding.
• Active daily use of AI coding assistants (GitHub Copilot, Cursor, Claude Code or equivalent) and frontier LLMs (Claude, GPT‑4o, Gemini), fluent across the full SDLC and able to coach a team of 8–15 engineers in AI‑native practices.
• Proven hands‑on experience designing, building and deploying MCP server ecosystems at project or account scale — including security controls, versioning and observability.
• Demonstrated ability to architect and operate end‑to‑end agentic SDLC pipelines that integrate with real enterprise tools via MCP and APIs, built and run in production rather than only in a proof of concept.
• Experience evaluating and selecting AI agent orchestration frameworks (LangGraph, CrewAI, AutoGen, Spring AI Agents or equivalent) for production use with documented rationale and trade‑offs.
• Track record of improving a team’s AI maturity with measurable change supported by adoption metrics or productivity evidence.
• Demonstrated learning agility at team scale, showing that your team’s engineering practices changed meaningfully in the last 12 months because of evolving frontier models and tools and that you drove that change.
• English proficiency: Upper‑Intermediate or above (B2+).
• Nice to have: Experience with RAG pipelines, LLM fine‑tuning or LLM evaluation frameworks (RAGAS, DeepEval or similar) applied to software engineering contexts.
• Hands‑on experience with structured agentic SDLC methodologies — specification‑driven AI development, specification hardening or equivalent governed delivery protocols.
• Experience with Managed Services or AIOps delivery models: autonomous monitoring, AI‑assisted incident response or intelligent operations pipelines.
• Capability to design function calling and tool‑use across multiple frontier models, building reliable governed tool‑use chains.
• Contributions to internal AI maturity assessments, team certification programmes or AI engineering playbooks.