Lead Java Engineer - AI Native

Role Overview

Responsibilities

• Design, develop, and maintain scalable Java applications using Spring Boot and microservices architecture.
• Build and deploy MCP servers that expose Java services, databases, or internal tools to LLM-based agents.
• Implement agentic SDLC pipelines covering specifications, code generation, testing, CI/CD, and deployment validation.
• Integrate agentic pipelines with Jira, Confluence, GitHub, ServiceNow, and observability platforms.
• Use AI coding assistants and frontier LLMs throughout the development lifecycle and evaluate outputs for correctness and security.
• Identify AI-leverage opportunities and contribute prompt templates, reusable agent patterns, and MCP connectors.
• Conduct code and architecture reviews and mentor junior and mid-level engineers.
• Maintain automated test coverage and healthy CI/CD practices.
• Track frontier model, agent framework, and MCP connector developments.

Core Requirements

• 8–12 years of professional Java development with ownership of complex production systems.
• Deep expertise in Spring Boot, Spring Cloud, Spring Data, Spring Security, and microservices patterns.
• Strong architecture skills across distributed systems, event-driven architecture, DDD, and CQRS/event sourcing.
• Cloud-native engineering experience on AWS, GCP, or Azure, including infrastructure as code and observability.
• Experience leading technical teams through architecture governance, coding standards, mentoring, and onboarding.
• Daily use of AI coding assistants and frontier LLMs, with ability to coach 8–15 engineers.
• Hands-on experience designing, building, and deploying MCP server ecosystems with security, versioning, and observability.
• Production experience architecting agentic SDLC pipelines integrated with enterprise tools through MCP and APIs.
• Experience evaluating AI agent orchestration frameworks for production use.
• English proficiency at Upper-Intermediate level or above, equivalent to B2+.

Additional Qualifications

• A track record of improving team AI maturity with measurable adoption or productivity evidence is required.
• Demonstrated learning agility at team scale through meaningful changes driven by evolving frontier models and tools is required.
• Experience with RAG pipelines, LLM fine-tuning, or LLM evaluation frameworks is nice to have.
• Experience with structured agentic SDLC methodologies is nice to have.
• Managed Services or AIOps delivery experience is nice to have.
• Experience designing governed function-calling and tool-use chains is nice to have.
• Contributions to AI maturity assessments, certification programs, or engineering playbooks are nice to have.