The candidate should have hands-on experience with agent orchestration, prompt engineering, Retrieval-Augmented Generation (RAG), LLM evaluation, observability, and cloud-based AI deployments. This role requires strong software engineering fundamentals combined with practical experience building scalable, secure, and cost-efficient AI applications.
Design, develop, and maintain scalable backend services and production APIs using Java 21+ and Spring Boot 3.x.
Build and integrate AI agents using Spring AI or LangChain4j within enterprise Java applications.
Develop effective prompt templates, system instructions, role definitions, and constraints for LLM-powered applications.
Implement agentic workflows involving tool calling, memory management, planning, retries, and guardrails.
Design and develop evaluation frameworks to measure LLM response quality, accuracy, reliability, and performance.
Implement LLM observability and monitoring using tools such as Langfuse, Arize, Weights & Biases, or Datadog.
Monitor and optimize model traces, response latency, token consumption, cost, and failure rates.
Apply RAG techniques, including document chunking, embeddings, vector databases, and retrieval optimization.
Optimize LLM performance and operational costs through caching, batching, model routing, and prompt/token optimization.
Evaluate and select AI models based on response quality, latency, cost, and risk.
Deploy and manage scalable, secure AI services across AWS, Azure, or Google Cloud Platform environments.
Collaborate with engineering teams to implement AI-driven software development practices and production-ready solutions.
Strong hands-on experience with Java 21+ and Spring Boot 3.x.
Proficiency in Spring Web, Spring Data, and Spring Security.
Experience building production-grade REST APIs and backend microservices.
Hands-on experience with Spring AI or LangChain4j.
Strong understanding of Generative AI, LLMs, and agentic AI architecture.
Practical experience in prompt engineering and prompt optimization.
Experience with AI agent orchestration, tool calling, memory, planning, retries, and guardrails.
Knowledge of RAG architecture, embeddings, vector databases, and retrieval tuning.
Experience designing and implementing LLM evaluations and quality benchmarks.
Familiarity with LLM observability platforms such as Langfuse, Arize, Weights & Biases, or Datadog.
Experience with LLM performance monitoring, cost optimization, and model selection.
Cloud deployment experience with AWS, Azure, or Google Cloud Platform.
Familiarity with AI coding assistants such as GitHub Copilot or Amazon Q.
Never miss an opportunity! Create an alert based on the job you applied for.
