AI Native Engineer

Job description

MUST-HAVE REQUIREMENTS

Java Engineering

• 6-12 years of hands-on Java development in production environments
• Strong proficiency in Spring Boot, Spring MVC, Spring Security, and RESTful API design
• Solid experience with microservices and event-driven patterns (Kafka, RabbitMQ, or similar)
• Cloud platform experience AWS, GCP, or Azure including containerization (Docker, Kubernetes)
• Working knowledge of relational (PostgreSQL, MySQL) and NoSQL (MongoDB, Redis) databases
• CI/CD pipelines (Jenkins, GitHub Actions, GitLab CI) and DevOps engineering practices

AI Native Capabilities

• Active daily use of AI coding assistants (GitHub Copilot, Cursor, Claude Code, or equivalent) and frontier LLMs fluent, not experimental
• 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 an agentic workflow or pipeline that connects multiple tools or services via LLM-orchestrated agents
• Ability to integrate agentic pipelines with enterprise systems via MCP or REST/event APIs must have built it, not just read about it
• Working knowledge of at least one agent orchestration framework: LangChain, LangGraph, CrewAI, AutoGen, or Spring AI Agents
• Strong critical evaluation of AI-generated code: able to identify correctness issues, security gaps, and performance problems in AI outputs
• Genuine learning agility: can describe how your engineering practice changed meaningfully in the last 6–12 months due to new AI tools or model capabilities
• English proficiency: Upper-Intermediate or above (B2+)

NICE TO HAVE

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