Key Responsibilities

• Build and deploy Gen-AI applications using RAG, LLMs, and embeddings.
• Design, implement, and optimize RAG pipelines using vector databases and prompt engineering.
• Develop and maintain backend systems using Next.js (API routes) and FastAPI.
• Collaborate with frontend developers to integrate AI services with React/Next.js applications.
• Write clean, scalable code with robust documentation and testing practices.
• Stay updated on advancements in AI (especially open-source LLMs, RAG stacks, LangChain/LlamaIndex, etc.) and recommend improvements.

Technical Skills Required

• Languages: Proficient in Python, JavaScript/TypeScript.
• Backend: Experience with FastAPI, Next.js API routes.
• Frontend: Comfortable with React, Next.js.
• AI/ML Concepts: Understanding of LLMs, embeddings, vector stores (e.g., Pinecone, FAISS, Weaviate), and RAG workflows.
• Tools & Libraries: Familiarity with LangChain, LlamaIndex, OpenAI APIs
• DevOps: Experience with Docker, GitHub Actions, or cloud deployment (e.g., Vercel, AWS, GCP).

Soft Skills & Attributes

• Curiosity and eagerness to learn.
• Strong problem-solving and debugging skills.
• Excellent communication and collaboration skills.
• Ability to work in fast-paced startup environments and take ownership.