Skip to content
View CodeNinjaSarthak's full-sized avatar

Block or report CodeNinjaSarthak

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
CodeNinjaSarthak/README.md
Typing SVG

AI/ML Engineer crafting end-to-end intelligent systems — from LLM agents to real-time computer vision 🚀

LinkedIn Email GitHub Kaggle LeetCode

Profile Views

🧠 About Me

class SarthakChauhan:
    def __init__(self):
        self.role = "AI/ML Engineer & Researcher"
        self.education = "B.Tech CSE (AI/ML) @ Bennett University"
        self.achievements = "CGPA: 9.42/10.0 | Dean's List (Top 10%)"
        self.location = "India 🇮🇳"
        
    def current_work(self):
        return [
            "🔬 Building RAG systems with curriculum-aligned content at Cograd",
            "🚗 YOLOv8 + dehazing for foggy traffic detection (Funded Project)",
            "🧠 BraTS-2020 tumor segmentation with Dice optimization",
            "💬 Hinglish NLP with mBERT/XLM-R achieving 90.7% accuracy"
        ]
    
    def skills(self):
        return {
            "AI/ML": ["Deep Learning", "NLP", "Computer Vision", "RAG", "PINNs"],
            "LLM Stack": ["LangChain", "LlamaIndex", "CrewAI", "AutoGen", "LangGraph"],
            "Frameworks": ["PyTorch", "TensorFlow", "Hugging Face", "FastAPI"],
            "MLOps": ["Docker", "MLflow", "W&B", "ONNX", "TensorRT"]
        }
    
    def fun_fact(self):
        return "I think my GPU works harder than I do 😄"

🚀 Featured Projects

DataWhiz

Text-to-SQL System with Multi-Agent Orchestration

🗃️ Handles 200+ table databases with GPT-4o + LangChain
🎯 35% error reduction via vector schema retrieval
📊 3.2x faster insights with LIDA auto-visualization (N=12 user study)

FastAPI LangChain DuckDB Neo4j Azure

Aurigen

AI Jewelry Design Studio

💎 Fine-tuned SDXL + LoRA on 6K jewelry images
🎨 ControlNet for geometric constraint preservation
⚡ FP16 optimization: 8.2s → 2.1s per image

SDXL ControlNet LoRA PyTorch Streamlit

AI-Powered Live Class Doubt Management

Real-time Doubt Clustering for Live Sessions

🎓 68% reduction in instructor response time (200-doubt simulations)
⚡ Async LLM pipeline with instructor verification loop
📈 Supports 100+ concurrent doubts in YouTube live

FastAPI LLMs pgvector Redis

RAG Content Generator

Enterprise RAG System @ Cograd

📚 Deployed across 20+ teachers in 3 schools
✅ 78% of content required minimal editing
💰 25-30% LLM cost reduction via compression & caching
⚡ Supports 50+ concurrent users

Qdrant MongoDB FastAPI PostgreSQL Redis

---

🎯 Skills

🧠 AI/ML & Research

  • Machine Learning, Deep Learning
  • Natural Language Processing (NLP)
  • Computer Vision (YOLOv8, Dehazing, Detection)
  • Transformers, LLMs, RAG Systems
  • Physics-Informed Neural Networks (PINNs)
  • Diffusion Models (SDXL, ControlNet)
  • Optimization, Feature Engineering, Statistical Modeling

🤖 LLM & Agents

  • LangChain, LlamaIndex, LangGraph
  • AutoGen, CrewAI, JinaAI
  • Prompt Engineering & Retrieval Optimization
  • Multi-Agent Systems for SQL, Automation & Pipelines
  • Vector Search & Embeddings
  • OpenAI API Integration

📚 Frameworks & Libraries

  • PyTorch, TensorFlow, Hugging Face
  • scikit-learn, OpenCV, NumPy, Pandas
  • FastAPI, Streamlit, DuckDB, MongoDB
  • Qdrant, Neo4j, PostgreSQL, MySQL

⚙️ MLOps & Systems

  • Docker, MLflow, Weights & Biases
  • ONNX, TensorRT (FP16/INT8 optimization)
  • Azure, GCP, Linux
  • Grafana, Prometheus, CI/CD
  • Experiment Tracking, Profiling & Deployment
  • CUDA, LaTeX

🛠️ Tech Stack

💻 Languages

Python C++ Java SQL

🧠 Deep Learning & AI

PyTorch TensorFlow Hugging Face Transformers scikit-learn OpenCV Stable Diffusion ControlNet PINNs

🤖 LLM Ecosystem

LangChain LlamaIndex LangGraph CrewAI AutoGen JinaAI OpenAI Embeddings Vector Search

🚀 Backend & Deployment

FastAPI Streamlit MongoDB DuckDB PostgreSQL MySQL Docker Azure GCP

📊 MLOps & Optimization

MLflow Weights & Biases Grafana Prometheus ONNX TensorRT CUDA Qdrant Neo4j

🔧 Tools

Git Linux MATLAB LaTeX


📊 GitHub Profile Stats

🔥 Streak Stats

GitHub Streak



📈 Contribution Graph


🐍 Contribution Graph

github-snake

🏆 Achievements

🥇 Hackathons & Competitions 🎓 Academic 📜 Certifications
Amazon ML Challenge 2024
Top 0.5% (409/74,823)
Dean's List Award
Top 10%
IBM Machine Learning
IIT Bombay Convolve
Top 50/4,189 Teams
CGPA: 9.42/10.0 Deep Learning Specialization
Kharagpur Data Science
Semi-finalist
Published @ IC3SE 2025 GenAI with LLMs

📚 Research & Publications

📄 "Deep Learning-based Brain Tumor Detection" (Second Author)
Accepted & Presented at IC3SE 2025, IEEE UP Section

📄 "Hinglish Abusive Comment Detection Using Transformer-Based Models" (First Author)
Accepted at AICAPS 2026, IEEE Kerala Section co-sponsored


💭 Dev Quote

Dev Quote

🤝 Let's Connect!

I'm always excited to collaborate on innovative AI/ML projects!

💼 Open to: Research Collaborations | Open Source | AI/ML Internships

📧 Reach me at: sarthak4156@gmail.com



Popular repositories Loading

  1. AeroPINN AeroPINN Public

    Leveraging Physics-Informed Neural Network(PINN) to simulate airflow patterns around arbitrary geometries(AirFoils) in real-time.

    Jupyter Notebook 5 1

  2. Aurigen-AI-Powered-Jewelry-Design-Studio Aurigen-AI-Powered-Jewelry-Design-Studio Public

    Jupyter Notebook 2

  3. Landmark_detection Landmark_detection Public

    Streamlit web app for scene classification using Vision Transformer (ViT). Upload images to classify into 6 categories: Buildings, Forest, Glacier, Mountain, Sea, Street.

    Jupyter Notebook 2

  4. health-check health-check Public

    Scripts that checks the health of computers

    Python 1

  5. it-cert-automation-practice it-cert-automation-practice Public

    Forked from google/it-cert-automation-practice

    Google IT Automation with Python Professional Certificate - Practice files

    Python 1

  6. music music Public

    scripts for making a music app

    Java 1