Presentation
I Can Help You With:
ML & Deep Learning models (classification, regression, forecasting)
NLP projects (text classification, sentiment, summarization, embeddings)
LLM applications (RAG pipelines, chatbots, agent workflows)
Computer vision models (CNNs, image classification, detection)
AI-powered web apps (FastAPI, Flask, Streamlit)
Model deployment (APIs, Docker, Render, Hugging Face, AWS)
Data analysis, preprocessing, automation & pipelines
Why Clients Work With Me
BS in Computer Science with hands-on AI experience
I build complete solutions: model → API → UI → deployment
Clear communication, clean code, and reliable delivery
I focus on business impact, not just technical outputs
Recent Work:
Phishing URL Detection (MLOps) – End-to-end pipeline with MLflow, Dockerized FastAPI, AWS EC2 deployment
Potato Disease Classifier (Deep Learning) – CNN model + FastAPI backend + Flask UI for real-time predictions
YouTube Video Summarizer (GenAI) – Streamlit app using GPT-4o for transcript extraction & summarization
If you are looking for someone who can build, explain, and deploy intelligent systems, let’s work together.
Send me a message anytime. I am happy to help.
Background
• Engineered an internal recruiter automation tool, reducing manual candidate screening time by 40% through streamlined workflows.
• Optimized LLM performance via advanced prompt engineering and deployed scalable AI services using REST APIs.
• Architected data pipelines to ensure seamless integration between AI models and end-user applications.
Specialized Coursework: Natural Language Processing (NLP), Data Warehousing & Mining, Advanced Software Engineering, and Distributed Database Systems.
Core Strengths: Strong theoretical foundation in Algorithms, Statistics, and Probability, combined with practical expertise in Object-Oriented Programming (OOP).
Technical Expertise:
Generative AI & LLMs: Experienced in building RAG (Retrieval-Augmented Generation) systems and prompt-engineered workflows using LangChain and GPT-4o.
MLOps & Deployment: Proficient in the end-to-end ML lifecycle—including data preprocessing, model training, and containerized deployment using Docker and FastAPI on cloud environments (AWS).
Data Engineering: Skilled in managing complex data structures, SQL/NoSQL databases, and building ETL pipelines for AI training.
