Job
Description
Job Description Java Developer with expertise in Prompt Engineering to join our AI-driven development team. The ideal candidate will combine robust Java backend development capabilities with hands-on experience in integrating and fine-tuning LLMs (e.g., OpenAI, Cohere, Mistral, or Anthropic), designing effective prompts, and embedding AI functionality into enterprise applications. This role is ideal for candidates passionate about merging traditional enterprise development with cutting-edge AI technologies. Key Responsibilities Design, develop, and maintain scalable backend systems using Java (Spring Boot) and integrate AI/LLM services. Collaborate with AI/ML engineers and product teams to design prompt templates, test prompt effectiveness, and iterate for accuracy, performance, and safety. Build and manage RESTful APIs that interface with LLM services and microservices in production-grade environments. Fine-tune prompt formats for various AI tasks (e.g., summarization, extraction, Q&A, chatbots) and optimize for performance and cost. Apply RAG (Retrieval-Augmented Generation) patterns to retrieve relevant context from data stores for LLM input. Ensure secure, efficient, and scalable communication between LLM APIs (OpenAI, Google Gemini, Azure OpenAI, etc.) and internal systems. Develop reusable tools and frameworks to support prompt evaluation, logging, and improvement cycles. Write high-quality unit tests, conduct code reviews, and maintain CI/CD pipelines using tools like Jenkins, GitHub Actions, or GitLab. Work in Agile/Scrum teams and contribute to sprint planning, estimation, and retrospectives. Must-Have Technical Skills Java & Backend Development : Core Java 8/11/17 Spring Boot, Spring MVC, Spring Data JPA RESTful APIs, JSON, Swagger/OpenAPI Hibernate or other ORM tools Microservices architecture Prompt Engineering / LLM Integration : Experience working with OpenAI (GPT-4, GPT-3.5), Claude, Llama, Gemini, or Mistral models. Designing effective prompts for various tasks (classification, summarization, Q&A, etc.) Familiarity with prompt chaining, zero-shot/few-shot learning Understanding of token limits, temperature, top_up, and stop sequences Prompt evaluation methods and frameworks (e.g., LangChain, LlamaIndex, Guidance, PromptLayer) AI Integration Tools : LangChain or LlamaIndex for building LLM applications API integration with AI platforms (OpenAI, Azure AI, Hugging Face, etc.) Vector databases (e.g., Pinecone, FAISS, Weaviate, ChromaDB) DevOps / Deployment : Docker, Kubernetes (preferred) CI/CD tools (Jenkins, GitHub Actions) AWS/GCP/Azure cloud environments Monitoring : Prometheus, Grafana, ELK Stack Good-to-Have Skills Python for prototyping AI workflows Chatbot development using LLMs Experience with RAG pipelines and semantic search Hands-on with GitOps, IaC (Terraform), or serverless functions Experience integrating LLMs into enterprise SaaS products Knowledge of Responsible AI and bias mitigation strategies Soft Skills Strong problem-solving and analytical thinking Excellent written and verbal communication skills Willingness to learn and adapt in a fast-paced, AI-evolving environment Ability to mentor junior developers and contribute to tech strategy Education Bachelors or Masters degree in Computer Science, Engineering, or related field Preferred Certifications (Not Mandatory) : OpenAI Developer or Azure AI Certification Oracle Certified Java Professional AWS/GCP Cloud Certifications (ref:hirist.tech)
