The role involves driving the evolution of enterprise applications by embedding multi-step Large Language Model reasoning. The engineer will build intelligent AI agents and integrate them into a large-scale Java and Spring Boot ecosystem. Responsibilities include designing complex Retrieval-Augmented Generation pipelines and establishing enterprise guardrails for safety and compliance. The position requires defining evaluation metrics to monitor model accuracy, latency, and operational costs. Additionally, the role involves providing technical leadership and mentoring development teams on architectural decision-making regarding agent-based systems.

The role requires at least eight years of progressive software engineering experience with a strong foundation in enterprise Java and Spring Boot. Candidates must possess deep hands-on expertise in LangChain, LangGraph, and prompt engineering, including structured outputs and tool calling. Proficiency in building and scaling RAG pipelines, working with vector databases, and implementing AI evaluation frameworks like DeepEval is necessary. Furthermore, the position demands a background in distributed systems and the ability to translate complex business problems into secure, production-ready systems.