Machine Learning Engineer

Specializing in Large Language Models and RAG systems. Building production ML infrastructure and sharing deep technical implementations from first principles.

Read My Blogs

View Projects

About Me

I'm a Machine Learning Engineer specializing in Large Language Models and Retrieval-Augmented Generation (RAG) systems. Currently at Verloop.io, I architect end-to-end RAG pipelines that power customer support for enterprise clients across e-commerce, banking, and healthcare sectors.

I believe in understanding AI systems at a fundamental level—from transformer architectures to retrieval optimization. Through my technical blog, I break down complex topics like Rotary Positional Embeddings (RoPE), attention mechanisms (MHA, GQA, MLA), and modern LLM architectures, providing complete PyTorch implementations from scratch.

My work bridges cutting-edge research and production systems. I focus on building with clarity, sharing knowledge openly, and making advanced ML techniques accessible to practitioners. Previously at Monsoon CreditTech, I built credit risk models achieving 40% reduction in delinquency rates.

LLMs

Specialist

RAG

Systems

Production

ML Systems

Skills & Expertise

Technologies and areas I work with

🤖

LLM & AI

Large Language Models
RAG Systems
Retrieval Systems
Vector Databases
Embedding Models
Prompt Engineering
Transformer Architecture

🧠

ML Frameworks

PyTorch
Hugging Face Transformers
Scikit-learn
XGBoost
Weights & Biases
SHAP
Optuna

⚙️

Infrastructure

Docker
Kubernetes
gRPC
Kafka
RabbitMQ
Redis
PostgreSQL
MySQL

💻

Languages & Web Frameworks

Python
SQL
FastAPI
Django
Gradio

☁️

Cloud & DevOps

Google Cloud Platform
CI/CD
GitHub Actions
Git

✨

Expertise

Deep Learning
Natural Language Processing
Mathematics
Microservices Architecture

Experience & Education

My professional journey and key achievements

SDE - Machine Learning

Verloop.io

Oct 2024 - Present

Building production RAG systems and LLM infrastructure for enterprise customer support automation.

Architected end-to-end RAG pipeline supporting multiple document formats (PDF, Markdown, Text) for enterprise clients
Improved retrieval accuracy by 15% (Recall) and 5% (MRR) through systematic evaluation of embedding models and rerankers
Built production microservices with Docker, Kubernetes, gRPC, and integrated Weaviate vector database
Optimized LLM context windows, reducing latency and API costs while maintaining answer quality

Machine Learning Engineer

Monsoon CreditTech

Feb 2022 - Aug 2024

Developed ML models for credit risk assessment and fraud detection in fintech.

Reduced loan delinquency rates by 40% through credit risk model using XGBoost and Bayesian optimization
Implemented comprehensive MLOps monitoring suite with drift detection (PSI, KS test) and SHAP explainability
Deployed scalable REST APIs using FastAPI and Django, containerized with Docker on GCP Cloud Run
Built fraud detection model using deep isolation forest, identifying 30% of anomalies in top risk decile

Bachelor of Science in Computer Science

BML Munjal University

Jul 2016 - Aug 2020

Major in Computer Science and Engineering. Published research in Nature Scientific Reports.

Published: "Machine learning predicts live-birth occurrence before IVF treatment" in Nature Scientific Reports (2020)
Focused on Machine Learning, Deep Learning, and Software Engineering

Featured Projects

Open-source projects spanning LLMs, ML, and data engineering

Featured

AI Research Agent

Autonomous research agent that decomposes queries, executes multi-turn tool calling with web search and arXiv, and validates completeness through self-reflection. Features real-time Streamlit UI.

LLMAI AgentsRAG

PythonGoogle GeminiStreamlit+1 more

View on GitHub

Featured

Weaviate MCP Inspector

Natural language interface for Weaviate vector databases through Claude using Model Context Protocol. Enables intuitive database exploration via conversation with 9 inspection tools.

Vector DBMCPTools

PythonWeaviateFastMCP+1 more

View on GitHub

Featured

Handwritten Text Recognizer

Deep learning OCR system with ResNet encoder and Transformer decoder (14M parameters). Achieves 70% error reduction via augmentation. Deployed as FastAPI microservice on GCP with monitoring.

Computer VisionDeep LearningMLOps

PyTorchFastAPIDocker+1 more

View on GitHub

View All Projects