Lead Senior AI Native Engineer Java
Posted:
18 November 2026 (Yesterday)
Application Deadline:
15 February 2027
Vacancies:
1 Vacancy
Job Summary
We are looking for a Lead / Senior AI Native Engineer - Java to design build and scale agentic AI pipelines and enterprise Java systems combining deep software engineering expertise with hands-on experience in multi-agent orchestration MCP servers and AI-native development practices.
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 MCP servers that expose Java services databases or internal tools to LLM-based agents enabling agents to inspect generate and validate against live enterprise systems
- Build and extend the Agentic Workflow pipeline itself: orchestrator agents producer agents validator agents and the skills that parameterize them across the discovery architecture design and forward-engineering phases
- Onboard new client codebases business domains and target technology stacks onto the workflow by authoring technology adapters stack-specific implementation skills and section/validator skill pairs without forking the core pipeline
- Design and implement agentic SDLC loops: automated specification drafting AI-driven code generation intelligent test creation CI/CD integration and deployment validation each gated by deterministic scoring dimension floors and critical-issue auto-reject rules
- Integrate agentic pipelines with enterprise tools and platforms via MCP connectors or REST/event driven APIs
- Build React/Angular/JS frontends for modernized systems reproducing legacy UI fidelity from wireframes and design tokens where the engagement requires 1:1 behavioral replication
- Use AI coding assistants and frontier LLMs 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 the delivery area
- Contribute to the teams shared library of prompt templates reusable agent patterns skills and MCP connectors so the next client domain or stack onboards faster than the last
- 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 and healthy CI/CD pipeline practices and actively track frontier developments to bring relevant changes back to the team within weeks
Requirements
- 6 years of hands-on Java development in production environments with strong proficiency in Spring Boot Spring MVC Spring Security and RESTful API design
- Working proficiency in React Angular or modern JS/TypeScript frameworks for production UI delivery
- Solid experience with microservices and event-driven patterns such as Kafka or RabbitMQ
- Cloud platform experience with AWS GCP or Azure including containerization with Docker and Kubernetes
- Working knowledge of relational databases (PostgreSQL MySQL) and NoSQL databases (MongoDB Redis)
- Familiarity with CI/CD pipelines (Jenkins GitHub Actions GitLab CI) and DevOps engineering practices
- Active daily use of AI coding assistants (GitHub Copilot Cursor Claude Code or equivalent) and frontier LLMs
- Hands-on experience building and deploying at least one MCP server exposing APIs tools or data sources to an LLM agent
- Demonstrated experience designing or implementing a multi-agent pipeline with distinct agent roles explicit handoffs and a pass/fail or scored quality gate between steps
- Experience authoring reusable versioned skills or playbooks that encode domain/engineering judgment for agents to load
- Ability to integrate agentic pipelines with enterprise systems via MCP or REST/event APIs
- Capability to reverse-engineer requirements and domain models from legacy or unfamiliar codebases using AI-assisted analysis and translate them faithfully into a new target stack
- Practical context management skills including prompt/context window structuring retrieval and chunking strategies and multi-step agent memory management
- Experience implementing AI guardrails such as input/output validation PII redaction hallucination and scope-of-action checks and human-in-the-loop approval gates
- Working knowledge of tokenomics including token usage/cost estimation model selection trade-offs and designing agent workflows within latency/cost budgets
- AI/LLM security awareness including prompt-injection defense secure handling of secrets/credentials and least-privilege scoping for agent actions
- Strong critical evaluation skills for AI-generated code identifying correctness issues security gaps and performance problems
- Genuine learning agility with the ability to describe how engineering practice has evolved in the last 612 months due to new AI tools or model capabilities
Required Experience:
Staff IC