Python Developer (LLM & RAG) · Kolkata

Floydee Infotech Private is building next-generation AI-powered products leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and cloud technologies in Kolkata.

Responsibilities

• Design, develop, and maintain Python-based backend services and APIs.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for enterprise search and reasoning.
• Integrate Large Language Models from OpenAI, Anthropic, Gemini, or open-source models like Llama into products.
• Develop document ingestion, chunking, embedding, indexing, and semantic retrieval workflows.
• Work with vector databases such as Pinecone, Qdrant, ChromaDB, Weaviate, or FAISS.
• Implement prompt engineering, evaluation metrics, and response optimization techniques.
• Build high-performance REST APIs using FastAPI, Flask, or Django.
• Optimize AI applications for low latency, high throughput, scalability, and inference cost.
• Integrate cloud services on AWS or Azure for AI workloads.
• Collaborate with product managers and frontend engineers to deploy production-ready AI solutions.