Skip to content
View dipitvasdev's full-sized avatar

Organizations

@hackforla

Block or report dipitvasdev

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
dipitvasdev/README.md

๐Ÿ‘‹ Hi, I'm Dipit Vasdev!

๐ŸŽ“ AI Enthusiast | Full Stack Developer | Problem Solver


๐ŸŒŸ About Me

I'm a multi-hat-wearing engineer, passionate about leveraging AI, machine learning, and full-stack development to solve real-world problems. With a Masterโ€™s in Computer Engineering from NYU (Class of 2024), I love diving deep into core AI challenges, scaling solutions, and delivering impactful products. Whether it's optimizing a system or building from the ground up, I thrive in fast-paced startup environments.


๐ŸŽฉ Hats I Wear

๐ŸŽฉ The AI Engineer

  • Building NLP models, Vision Transformers, and multi-agent systems.
  • Fine-tuning models like DistilBERT, PyTorch, and TensorFlow for specific tasks.
  • Recent project: Created a spoiler-free movie review classifier with 78.49% accuracy.

๐ŸŽฉ The Full-Stack Developer

  • End-to-end web development using React, Next.js, Node.js, and Django.
  • Expertise in frontend-backend integrations with a focus on scalability and performance.
  • Built and deployed a recipe-sharing platform using React, AWS S3, and PostgreSQL.

๐ŸŽฉ The DevOps Guru

  • CI/CD pipelines with GitLab and automated deployments.
  • Scaled cloud infrastructure with Docker, Kubernetes, and AWS EC2.
  • Developed AWS Lambda functions to automate tasks, reducing cost by 25%.

๐ŸŽฉ The Data Scientist

  • Applied machine learning models like Isolation Forest for anomaly detection.
  • Data-driven decision making with NumPy, Pandas, and Matplotlib.
  • Built predictive maintenance solutions for large datasets with Scikit-learn.

๐Ÿ› ๏ธ Tech Stack

C++ Python JavaScript TypeScript
React Django NodeJS
AWS Docker
TensorFlow PyTorch


๐Ÿ’ก Notable Projects

๐ŸŽฌ Spoiler-Free Movie Reviews

  • Built a spoiler detection system using DistilBERT, achieving a high accuracy rate.
  • Designed to improve user experiences by removing spoilers in real-time.

๐Ÿš— Real-Time Car Anomaly Detection

  • Developed an anomaly detection model using Isolation Forest, improving detection accuracy with real-time data streams.
  • Achieved an F1 score of 0.86.

๐Ÿฒ Recipe Sharing Platform

  • Built a full-stack platform using React, AWS S3, PostgreSQL, and Django.
  • Implemented secure user authentication and scalable cloud infrastructure.

๐ŸŒฑ What I'm Learning Now

  • AI Agent Frameworks: Experimenting with multi-agent systems for customer support automation.
  • Advanced DevOps: Exploring new ways to optimize CI/CD pipelines with Kubernetes and Serverless Architectures.

๐ŸŽฒ Beyond the Code

  • Chess Enthusiast โ™Ÿ๏ธ: Improving strategic thinking, one move at a time.
  • Current Read ๐Ÿ“–: "Quiet: The Power of Introverts" by Susan Cain.
  • Gamer ๐ŸŽฎ: Exploring virtual worlds when Iโ€™m not building tech!

๐Ÿš€ Why Startups Love Me

  • ๐Ÿ”ฅ Startup Mindset: Iโ€™ve worked in fast-paced, dynamic environments where I wear multiple hats and contribute to all aspects of development.
  • ๐Ÿ’ก Full Ownership: Comfortable taking on high-ownership rolesโ€”I'm always excited to tackle challenges head-on, whether itโ€™s building a product from scratch or scaling an existing one.
  • ๐Ÿ“ˆ Data-Driven: I leverage data and AI to bring intelligent solutions to life. Startups need to move fast, and I make sure we scale smartly.

๐Ÿ“ซ Letโ€™s Connect

LinkedIn GitHub

Pinned Loading

  1. Recipe-Sharing-Platform-Django-Backend Recipe-Sharing-Platform-Django-Backend Public

    The Recipe Sharing Platform is a full-stack application featuring a React.js frontend and a Django backend. It enables users to create, update, and delete recipes, and manage user authentication. โ€ฆ

    Python

  2. Analyzing-Modern-Deep-Learning-Approaches-for-Spoiler-Detection-in-Text Analyzing-Modern-Deep-Learning-Approaches-for-Spoiler-Detection-in-Text Public

    When choosing to watch a movie or TV show, reviews and ratings are often relied upon to make informed decisions. However, these reviews can inadvertently reveal significant plot details, leading toโ€ฆ

    Jupyter Notebook 2 2

  3. Portfolio Portfolio Public

    A portfolio website built using Next.js 13, Tailwind CSS, and Framer Motion, showcasing a fully responsive design with light and dark modes. It features efficient email functionality integrated wiโ€ฆ

    TypeScript

  4. GitHub-Issue-Classifier GitHub-Issue-Classifier Public

    This project uses machine learning to categorize GitHub issues into types such as bug, enhancement, and question. Trained on Databricks using PySpark and scikit-learn, it achieves 85% accuracy withโ€ฆ

    TypeScript

  5. Multiplayer-Rock-Paper-Scissor Multiplayer-Rock-Paper-Scissor Public

    Rok Papr Scissor is a multiplayer game that can be played on computer devices. Two players point their hands (rock, paper and scissor) at the camera and then using computer vision techiniques compuโ€ฆ

    Jupyter Notebook

  6. PianoAi PianoAi Public

    Trained an LSTM Model to generate music using notes and chords. Then used, flask back end to deploy the model to web

    CSS