Senior Java Engineer - AI Native

EPAM Systems; Chennai District; Hybrid; INR 1,800,000 - 2,800,000; Full time

Job summary

EPAM Systems in India is seeking a Senior Java Engineer - AI Native to lead the design and delivery of scalable Java applications while embedding AI-native practices across the full software development lifecycle.

The role emphasizes building agentic pipelines and MCP integrations that connect enterprise systems to LLM-based agents, with three days in the office weekly and a strong focus on code quality, security, and reliability.

Qualifications

• 5–10 years of hands-on Java development in production.
• Proficiency with Spring Boot, Spring MVC and REST APIs.
• Experience with microservices, Kafka or RabbitMQ, and cloud platforms.

Responsibilities

• Design, develop and maintain scalable Java apps with Spring and microservices.
• Build MCP servers to expose services to LLM-based agents.
• Create agentic SDLC pipelines with AI-driven code generation and tests.
• Integrate MCP connectors with Jira, Confluence, GitHub and ServiceNow.
• Mentor juniors and maintain strong automated test coverage and CI/CD.

Skills

Java

Spring

Microservices

Cloud

Docker

Kubernetes

CI/CD

AI tools

MCP

English

Tools

Jenkins

GitHub Actions

GitLab CI

Kafka

RabbitMQ

Docker

Kubernetes

Jira

Confluence

ServiceNow

Job description

We are looking for a Senior Java Engineer - AI Native to join our team and drive the design and delivery of scalable Java applications while embedding AI-native practices across the full software development lifecycle. This role combines deep Java engineering expertise with hands-on experience building agentic pipelines and MCP integrations that connect enterprise systems to LLM-based agents. The position requires 3 days of work from the office.

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
• Architect and implement end-to-end agentic SDLC pipelines including 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 such as Jira, Confluence, GitHub and ServiceNow via MCP connectors or REST/event-driven APIs
• Use AI coding assistants and frontier LLMs across the full development lifecycle daily and critically evaluate AI outputs for correctness, security and edge cases before code commits
• Bring an AI-first mindset to automate repetitive engineering tasks, measure outcomes rather than activity and identify AI-leverage opportunities within the delivery area
• Contribute to the team's shared library of prompt templates, reusable agent patterns and MCP connectors
• Conduct code and architecture reviews and mentor Junior and Mid-level engineers in Java best practices and AI-native engineering methods
• Maintain strong automated test coverage across unit, integration, contract and AI-generated tests along with healthy CI/CD pipeline practices
• Track frontier developments such as new model releases, emerging agent frameworks and new MCP connectors, and bring relevant changes back to the team within weeks

Requirements

• 5-10 years of hands-on Java development experience in production environments
• Proficiency in Spring Boot, Spring MVC and Spring Security with RESTful API design
• Experience with microservices and event-driven patterns using Kafka or RabbitMQ
• Background in cloud platforms such as AWS, GCP or Azure including Docker and Kubernetes containerization
• Knowledge of relational databases such as PostgreSQL and MySQL alongside NoSQL databases such as MongoDB and Redis
• Familiarity with CI/CD pipelines including Jenkins, GitHub Actions and GitLab CI and DevOps engineering practices
• Active daily use of AI coding assistants such as GitHub Copilot, Cursor or Claude Code and frontier LLMs, applied fluently rather than experimentally
• Hands-on experience building and deploying at least one MCP server that exposes APIs, tools or data sources to an LLM agent
• Showcase of designing or implementing an agentic workflow or pipeline that connects multiple tools or services via LLM-orchestrated agents
• Capability to integrate agentic pipelines with enterprise systems via MCP or REST/event APIs through direct hands-on build experience
• Working knowledge of at least one agent orchestration framework such as LangChain, LangGraph or CrewAI
• Understanding of how to critically evaluate AI-generated code, identifying correctness issues, security gaps and performance problems, along with genuine learning agility reflected in evolving engineering practice over the last 6-12 months due to new AI tools or model capabilities
• Upper-Intermediate English proficiency or above (B2+)

Nice to have

• Experience building RAG (Retrieval-Augmented Generation) pipelines covering chunking, embedding and vector stores such as pgvector, Pinecone or Weaviate
• Skills in prompt engineering for development contexts including systematic prompt design, evaluation harnesses and iteration workflows
• Familiarity with LLM evaluation frameworks such as RAGAS or DeepEval to assess agent output quality
• Experience with function calling and tool-use APIs across multiple frontier models from Anthropic, OpenAI and Google
• Exposure to structured agentic SDLC methodologies such as spec-driven development with AI or specification hardening