Skip to content
View KshitijMittal's full-sized avatar

Highlights

  • Pro

Block or report KshitijMittal

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
KshitijMittal/README.md

Typing SVG

   


👋 About me

I'm a 2nd-year CS student specialising in AI/ML, building things that (hopefully) matter.

So far: a CV system for rural child health screening in India, an LLM agent that scored 0.80 on Medium difficulty at Meta's AI agent competition, and a CNN that taught me more about augmentation tradeoffs than about plant seedlings.

I care about systems that work in the real world — not just notebooks that pass. I'm most interested in LLMs, computer vision, and the gap between a model that works and one that ships.

Currently looking for an AI/ML or Data Engineering internship where I can build something real and learn fast.


🔭 What I'm working on

  • 🧪 Wrapping my House Price model in a Flask API — making it actually deployable, not just a notebook
  • 📖 Going deeper on LLM evaluation frameworks — prompted by what I saw scoring at Meta
  • 🛠 Improving the Vision Shield pipeline's accuracy and edge-case handling

🛠 Stack

Core ML / DL

Python PyTorch scikit-learn Pandas NumPy

LLMs & Deployment

Hugging Face Docker FastAPI Groq API

Computer Vision

OpenCV MediaPipe

Infra & Data

Git MySQL Jupyter


📌 Projects

Project What it does Result Deploy
🤖 Expense Audit Agent LLM agent auditing employee expenses against company policy — built for Meta's AI Agent Hackathon (2025). Owned inference.py, Dockerfile, and full Hugging Face Spaces deployment via Docker + Groq API (Llama 3.1). 0.80 Medium · 0.78 Hard · 0.67 Easy HF Spaces
👁 Vision Child Wellness Shield Non-invasive BMI estimation from live camera feeds using MediaPipe Pose + pixel-to-cm calibration. Built for rural health screening under India's Mid-Day Meal Scheme. Sole developer on cv-development branch. Height ±5–10% · Weight ±10–15% · 15 images Local
🌱 Plant Seedling Classification 3-block CNN classifying 12 species across ~4,750 images. Deliberately studied augmentation tradeoffs — found conditions where augmentation hurt generalisation. ~70% baseline accuracy Local
🏠 House Price Prediction End-to-end ML pipeline on 1,460 samples · 81 features. Deliberate imputation strategy + top-6 feature selection. Flask API wrapper in progress. R² ≈ 0.79 WIP

📊 GitHub Stats

  


github-snake

Pinned Loading

  1. Plant-Seedling-Classification Plant-Seedling-Classification Public

    A Deep Learning solution for Precision Agriculture that uses a CNN to classify 12 plant species, featuring a study on data augmentation to improve model robustness.

    Jupyter Notebook

  2. Vision-Based-Child-Wellness-Shield Vision-Based-Child-Wellness-Shield Public

    The Vision-Based Child Wellness Shield is an automated computer vision system that non-invasively estimates BMI and detects health symptoms from camera feeds for children in villages and coastal ar…

    Dart

  3. expense-audit-env expense-audit-env Public

    An AI-powered environment for auditing employee expense reports based on a set of company policies. This project is designed for AI agent competitions, where the goal is to build an agent that can …

    Python

  4. House-Price-Prediction House-Price-Prediction Public

    A complete end-to-end Machine Learning pipeline built in Python to predict house sale prices.

    Jupyter Notebook

  5. CodeAlpha-Artificial-Intelligence CodeAlpha-Artificial-Intelligence Public

    Showcasing innovative AI projects developed during the CodeAlpha Internship, combining machine learning, natural language processing, generative AI, and computer vision into practical solutions.

    Python

  6. leetcode-solutions leetcode-solutions Public

    My LeetCode journey, auto-updated daily. Each solution is organized by category with the full problem statement, runtime/memory stats, and my own notes on the approach.

    C++