Lead Java Engineer – AI Native

Epam Systems; Gurugram District; On-site; INR 3,000,000 - 5,500,000; Full time

Job summary

Epam Systems in India is seeking a Lead Java Engineer AI Native to own complex production systems and champion AI-native engineering practices. You will design, build and maintain scalable Java applications using Spring Boot, while delivering MCP-based services to AI agents and integrating with enterprise tools.

You will mentor engineers, drive end-to-end SDLC pipelines with AI-driven automation, and stay ahead of frontier models and tooling to improve delivery.

Qualifications

• Extensive Java development experience with Spring in production.
• Experience leading technical teams and architecture governance.
• Hands-on with MCP server ecosystems and integration patterns.
• Proficiency in AI-native SDLC and tooling across delivery teams.

Responsibilities

• Design, develop and maintain scalable Java applications using Spring Boot and microservices.
• Build MCP servers to expose Java services to LLM-based agents.
• Implement end-to-end AI-driven SDLC pipelines and CI/CD automation.
• Integrate agentic pipelines with Jira, Confluence, GitHub and other tools via APIs.
• Mentor junior engineers in Java best practices and AI-native methods.
• Review code and architectures, ensure automated test coverage and observability.

Skills

Java

Spring Boot

Microservices

AI/ML awareness

Mentoring

Architectural design

Tools

MCP

GitHub Copilot

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. In this role, you will combine deep Java expertise with hands‑on AI agent and MCP development to deliver scalable, intelligent solutions end‑to‑end.

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

• 812 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 815 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