About
Passionate AI/ML Engineer specializing in neural architecture design, transformer models, and production ML systems. Expert in developing machine learning models, building scalable data pipelines, and deploying AI solutions that learn and adapt.
Currently pursuing B.Tech in Data Science and AI at IIT Bhilai, where I serve as Coordinator of the DSAI Club.
My mission: reducing loss functions in both code and real-world problems.
Education
Indian Institute of Technology Bhilai
B.Tech. in Data Science and AI
Aug 2023 – May 2027 (Expected)
Relevant Coursework: Data Structures & Algorithms, ML, NLP, DBMS, Statistics, Probability, OS
Published Open Source
pytorch-dml
Deep Mutual Learning Library
Overview
Production-ready PyTorch library for Deep Mutual Learning (DML) and collaborative neural network training. Implements state-of-the-art techniques where multiple neural networks train together and learn from each other's predictions, achieving 2-5% higher accuracy compared to independent training.
Quick Start
pip install pytorch-dml
from pydml import DMLTrainer
from torchvision import models
models = [models.resnet18(), models.resnet18()]
trainer = DMLTrainer(models, device='cuda')
trainer.fit(train_loader, val_loader, epochs=100)
Package Contents
Projects
Student Performance Predictor
Architecture: XGBoost + Linear Regression Ensemble (R² = 0.989)
Built predictive models for academic risk assessment with Tableau dashboards. Achieved 20% earlier intervention through feature engineering and hyperparameter optimization.
Git Repository →PagedAttention Transformer
Innovation: Memory-Efficient KV Cache (60-80% reduction)
Implemented block-based attention mechanism with Copy-on-Write for beam search. Optimized inference pipeline achieving 2x throughput on large language models.
Git Repository →RAG Mental Health Assistant
Stack: LangChain + FAISS + GPT (93% relevance)
Deployed context-aware chatbot using Retrieval-Augmented Generation. Integrated semantic search with vector embeddings, containerized with Docker for scalability.
Git Repository →Academic Projects
Reciprocal Contextual Poetry Generation
Course: Machine Learning (CS 550)
Designed a modular experiment framework combining PPLM steering, a lightweight RLHF proxy (reward-model + supervised fine-tune), and hybrid inference-time control for generating context-aware poetry. Built reproducible pipelines for training, evaluation, and batch sweeps with aggregated metrics such as reward, perplexity, and distinctness.
View Repository →Bomberman AI — Intelligent Agent-Based Game (Tkinter)
Course: Artificial Intelligence (CSL304)
Built a full Bomberman game in Python with AI-driven bot agents capable of strategic movement, bomb placement, and real-time decision-making. Implemented A* pathfinding, state-based behavior (search, chase, evade), bomb safety simulation, and intelligent evasion scoring to create adaptive, challenging opponents. Includes customizable gameplay settings and full gameplay demo video.
view Repository →Skills
Languages
- Python
- SQL
- C++
- JavaScript
Frameworks
- PyTorch
- TensorFlow
- LangChain
- Hugging Face
- Flask
Tools & Cloud
- Git & Docker
- Linux
- AWS & GCP
- Streamlit & Jupyter
- Tableau & Plotly
Core Competencies
- Machine Learning
- NLP
- Model Deployment
- CI/CD
- Risk Analytics
Experience
AI Developer Intern
- Developed multi-agent automation systems that reduced manual effort by 40% and increased throughput by 30%
- Built secure REST APIs integrated with AWS and GCP, maintaining 99.9% uptime using CI/CD pipelines
- Optimized cloud infrastructure costs by 25% through performance tuning and risk assessment
- Enhanced system reliability by implementing real-time monitoring and data-driven automation
Team Lead — Autonomous Financial Intelligence Platform (NEXUS)
- Led an 8-member team to architect a production-grade multi-agent AI system combining real-time streaming, reinforcement learning, and LLM-based reasoning for autonomous market analysis, achieving 99.2% uptime with low-latency decision-making.
- Designed a 7-layer architecture with temporal data fabric, hybrid ML/RL forecasting, agentic debate framework, and a real-time risk engine featuring full explainability and auditability for financial decision-making.
- Built an end-to-end platform integrating live market, news, and social data with a causal knowledge graph, hybrid decision core, and an interactive command-center dashboard enabling transparent AI-driven portfolio management.
Achievements
- Amazon ML Challenge 2025: Ranked 278th nationwide with a score of 46.649
- Winner — Pixel Perfect Hackathon (IIT Bhilai): Led a cross-functional team to develop an AI solution under tight deadlines
- Top 10% — Data Science Bootcamp (IIT Guwahati): Ranked in the top decile among 500+ participants
- AI Content Creator: Authored 50+ AI/ML articles on Medium with 150+ monthly reads; active competitor on Kaggle
- Certifications: MLOps (Udemy), Edge AI and Computer Vision (Udemy), Algorithms and Data Structures Masterclass (Codedamn)