Abhijit

AI ML intern

Euron Learning Platform • Temps partiel

Aug 2025 - Present • 1 yr 3 mos

At Euron, I worked as an AI/ML Intern, gaining hands-on experience in AI/ML, Generative AI, Retrieval-Augmented Generation (RAG), backend development, and Big Data engineering. I built MediRAG, a full-stack AI-powered medical document analysis and retrieval platform that generates context-aware, source-backed responses from uploaded documents. I worked across the complete RAG pipeline, including document ingestion, text extraction, processing, chunking, embedding generation, semantic search, vector retrieval, and LLM-powered response generation. I used LlamaIndex and Hugging Face for document processing and embeddings, with Pinecone and FAISS for vector similarity search. I developed FastAPI backend APIs and integrated LLM workflows to deliver relevant, context-aware answers. For the frontend, I developed a responsive Next.js and React application for document upload, management, AI chat, and user interaction. PostgreSQL was used for application data and metadata, while Docker and Docker Compose enabled reproducible development and deployment. Alongside AI application development, I gained practical Big Data engineering experience with Hadoop, Apache Spark, Spark Streaming, Apache Kafka, Apache Airflow, Azure Data Factory, and AWS data services. I worked with data pipelines, large-scale data processing, real-time streaming, workflow orchestration, and cloud-based data engineering concepts. This experience strengthened my ability to build production-oriented AI applications and backend systems using Python, FastAPI, Next.js, React, SQL, PostgreSQL, RAG, LLMs, vector databases, semantic search, Docker, and modern AI/Big Data technologies. Key Skills: AI/ML | Generative AI | RAG | LLM Applications | LlamaIndex | Hugging Face | FastAPI | Python | Next.js | React | PostgreSQL | Pinecone | FAISS | Docker | Apache Spark | Hadoop | Kafka | Spark Streaming | Airflow | Azure Data Factory | AWS