LLM Developer (Node.js / Google Gemini SDK)

We are looking for an experienced LLM Developer (Node.js / Google Gemini SDK) to design and implement intelligent backend solutions leveraging Large Language Models (LLMs). The ideal candidate will have hands-on expertise with Google Gemini SDK and Node.js, developing APIs and services that power conversational AI, content generation, and automation workflows. Key Responsibilities: Develop and maintain Node.js-based APIs and microservices integrating LLMs using Google Gemini SDK and other AI APIs. Design scalable backend systems for AI-driven chat, summarization, and content generation. Implement and optimize prompt engineering and context management for high-quality LLM outputs. Integrate vector databases (e.g., Pinecone, Weaviate, ChromaDB) for retrieval-augmented generation (RAG). Collaborate with UI teams to build intelligent assistants and chat-based user experiences. Ensure security, performance, and cost optimization of AI workloads. Stay up to date with emerging AI frameworks, SDKs, and model releases (Gemini, OpenAI, Anthropic, etc.). Required Skills: Strong experience in Node.js and TypeScript/JavaScript development. Proven hands-on integration with Google Gemini SDK (@google/generative-ai) or equivalent LLM APIs. Solid understanding of RESTful/GraphQL APIs, microservice architecture, and cloud platforms (preferably GCP or AWS). Knowledge of prompt design, token handling, and response optimization for LLMs. Experience working with LangChain.js, LlamaIndex.js, or other orchestration frameworks. Strong debugging, testing, and documentation practices. Preferred Skills: Experience with React / Next.js for LLM-powered web apps. Familiarity with vector databases, embeddings, and retrieval-augmented pipelines (RAG). Understanding of Docker, Kubernetes, and CI/CD pipelines. Exposure to Python-based AI frameworks (optional).