Senior AI Engineer with 5+ years of experience building scalable AI-driven systems, APIs, and web applications.

My expertise is in engineering end-to-end Generative AI solutions, from large-scale data scraping to building and deploying RAG (Retrieval-Augmented Generation) pipelines. I am proficient in Python, Langchain, FastAPI, MongoDB (Atlas Vector Search), and React, with a strong background in DevOps, CI/CD, and cloud platforms.

• AI & ML: Generative AI, RAG, Langchain, Keras, TensorFlow, MongoDB Atlas Vector Search, Pytest
• Backend: Python, FastAPI, Flask, Django, PostgreSQL, MongoDB, MySQL, Redis
• DevOps & Cloud: AWS (EC2, SES, IAM), GCP, Heroku, Docker, Docker Compose, Jenkins, Git
• Frontend: Javascript, React

• Architected and deployed a RAG system handling over 5M documents, optimizing MongoDB Atlas Vector Search (HNSW) and retrieval techniques for sub-10-second responses.
• Integrated third-party AI services (Cohere embeddings/reranking, Gemini chat) and refactored the application architecture for efficient, scalable deployment on Heroku.
• Engineered and maintain the entire full-stack application, including the FastAPI backend, MongoDB database, and React frontend.

• Designed and optimized RESTful APIs with FastAPI, serving 500+ daily users.
• Reduced legacy process execution times by 30% through SQL tuning and code optimization.
• Built and maintained CI/CD pipelines (Jenkins, Docker), cutting deployment times by 40%.
• Boosted unit and integration test coverage to 80% across all applications.

Developed a Retrieval-Augmented Generation (RAG) system using LangChain, Ollama local models, and cloud-hosted models. Integrated Cohere for embeddings/reranking and Gemini for chatting. Optimized for a 5M+ document MongoDB collection with advanced indexing and retrieval techniques, deployed on Heroku with refactored architecture for scalability and low latency.

A scalable Django backend with RESTful APIs deployed on AWS EC2 using Docker. Implemented AWS SES integration for notifications and secure IAM roles for access control.

Developed a convolutional neural network achieving 92% accuracy in detecting COVID-19 from X-ray images using Python, Keras, and TensorFlow.

• MLOps practices for AI deployment and monitoring
• Fine-tuning RAG models for improved accuracy and precision
• Advanced Kubernetes orchestration
• System Design for distributed AI applications