Hi, I' m Mayank

I specialize in optimizing models and deploying
AI-driven solutions for real-world impact.

Profile

About

I am a Machine Learning Engineer and Data Scientist My focus lies in designing scalable machine learning models, automating workflows with MLOps, and optimizing systems for production deployment. Currently, I am focused on leveraging generative ai and llms to solve complex challenges while ensuring models are scalable, efficient, and production-ready.

Projects

Check out my work

I've worked on a range of machine learning projects. Here are a few that showcase my expertise and dedication to the field.

Fine-Tuning Large Language Models (LLMs)

Fine-Tuning Large Language Models (LLMs)

Fine-tuned various open-source LLMs including LLaMA 2, Mistral, Qwen, and vision-language models for domain-specific tasks. Leveraged efficient methods like LoRA, QLoRA, and quantization using Unsloth and Hugging Face.

LoRA
QLoRA
Unsloth
LLaMA 2
Mistral
Python
JSONL
Quantization
Hugging Face
Large Language Model (LLM) from Scratch

Large Language Model (LLM) from Scratch

Implemented a Large Language Model (LLM) from scratch, covering every stage from data preparation and model architecture to pretraining and fine-tuning. This project demystifies transformer-based models through hands-on code and experiments, enabling a deeper understanding of attention mechanisms and token prediction.

Python
NumPy
PyTorch
Transformer Architecture
Attention Mechanism
Word Embeddings
Instruction Tuning
Fine-tuning
LLM Pretraining
US Visa Approval Prediction using MLOps

US Visa Approval Prediction using MLOps

Built an end-to-end MLOps pipeline to predict the approval status of US visa applications. Implemented machine learning models, deep learning techniques, and automated deployment pipelines.

FastAPI
Docker
AWS Cloud Services
GitHub Actions
XGBoost
Custom ANN
MongoDB
Evidently AI
Streamlit
MLflow
Python
Pandas
Scikit-Learn
Interactive ML Algorithm Visualizer

Interactive ML Algorithm Visualizer

An interactive web application designed to help users understand and experiment with machine learning algorithms visually. It offers dynamic visualizations for concepts like linear regression, allowing users to adjust parameters such as slope and intercept interactively. The platform aims to simplify ML concepts for learners through intuitive design and engaging tools.

TypeScript
D3.js
SVG
Next.js
Network Security - Malicious URL Detection using MLOps

Network Security - Malicious URL Detection using MLOps

Developed an end-to-end MLOps project to detect malicious URLs using XGBoost. Integrated robust pipelines for data ingestion, model training, deployment, and monitoring.

Streamlit
FastAPI
XGBoost
MongoDB
Apache Airflow
MLflow
GitHub Actions
Docker
AWS S3
AWS EC2 Instance
Customer Satisfaction Prediction using ZenML

Customer Satisfaction Prediction using ZenML

Predicted customer satisfaction scores for future orders using historical e-commerce data from the Brazilian E-Commerce Public Dataset by Olist. This project leverages multiple machine learning models like CatBoost, XGBoost, and LightGBM, built within a ZenML pipeline to create a production-ready solution.

XGboost
Optuna
ZenML
Streamlit
MLFlow

Latest Blogs


Loading blogs...

Some of My Lectures

A visual introduction to tokenization in LLMs | Byte Pair Encoding Algorithm

A visual introduction to tokenization in LLMs | Byte Pair Encoding Algorithm

March 13, 2025

In this video, I have explained tokenization in Large Language Models (LLMs) in a visual manner.

BPE
Tokenization
LLMs

Skills

Get in Touch

Want to chat? Just shoot me a dm with a direct question on twitter and I'll respond whenever I can. I will ignore all soliciting.