Projects & Publications
A showcase of my technical projects, research work, and contributions to the field of computer science and software engineering.
Publications
Automatic Generation of Math Word Problems for Assessing Learner Skills in Adaptive Learning Systems
PublicationFebruary 2022, Hyderabad, India
Generated algebra math word problems using neural networks for enhancing intelligent tutoring in adaptive learning systems, reducing manual effort by 40%. Achieved a 60% increase in BLEU scores using transformer-based LLM models GPT-2 and TFGPT2LMHead (with Char-LSTM as a baseline), enhancing problem generation accuracy and quality.
Featured Projects
Distributed Stock Trading Application
Designed and deployed a scalable 3-tier microservices-based stock trading system using Spring Boot and REST APIs on AWS EC2, supporting 15+ concurrent users.
Key Achievements
- Optimized backend performance with an LRU cache and server-push invalidation in the frontend, reducing stock query response time by ~35% under load
- Implemented fault-tolerant leader-follower replication and recovery for the order service using REST-based synchronization, ensuring 100% consistency post-crash with under 1s failover latency
Applied Reinforcement Learning Systems & Optimization
Designed, analyzed, and optimized end-to-end policy learning systems including policy gradients, value-based, and evolutionary methods. Achieved near-optimal performance through rigorous experimentation, theoretical grounding, and sample-efficient optimization.
Key Achievements
- Built and evaluated reinforcement learning systems end-to-end, implementing policy gradients, Actor-Critic, SARSA, Q-Learning, TD-Learning, Monte Carlo, and evolutionary RL (PI²-CMA-ES) from scratch, enabling systematic comparison of on-policy vs off-policy and gradient-free vs gradient-based methods.
- Optimized convergence and sample efficiency through controlled experimentation, achieving ≤0.1 Max-Norm error in policy evaluation within ~1.6K–1.9K episodes and stabilizing TD-Learning to converge in ~795 episodes on average via hyperparameter tuning, exploration scheduling, and variance reduction.
- Translated RL theory into scalable implementations, deriving Bellman equations, optimality guarantees, and contraction properties, and operationalizing them using tile coding (2K+ features), ε-greedy/softmax exploration, advantage estimation, and covariance adaptation.
Distributed Image Processing System
Built a Dockerized image classification pipeline using Hadoop HDFS to store 25,000 images from the Kaggle Dogs vs. Cats dataset, and Spark for parallel inference.
Key Achievements
- Preprocessed images with OpenCV and applied a custom CNN and fine-tuned ResNet50 in PyTorch, achieving 78.1% and 96.3% accuracy
- Obtained 43 images/sec and 1.66x speedup with 2 Spark workers on 512 images; identified memory bottlenecks at 3 worker nodes
Music Note Generation with LSTM
Engineered an LSTM probabilistic model in PyTorch to predict next-note parameters (time, duration, value, volume) using softmax and categorical distributions.
Key Achievements
- Optimized training on 400,000+ variable-length MIDI files by implementing a custom Gaussian NLL loss function
- Achieved a 15% reduction in validation loss and improved training efficiency by 20% through hyperparameter tuning and early stopping
Coverfolio: Resume-to-Portfolio & Cover Letter Generator
Developed a full-stack web app enabling users to upload resumes and generate customizable portfolios or AI-driven cover letters, reducing content creation time by ~80%.
Key Achievements
- Built scalable system with React, Django GraphQL, PostgreSQL, and LLM parser achieving >95% accuracy in data extraction
- Integrated chatbot interface for AI-driven portfolio and cover letter rewrites with skill suggestions, enhancing personalization by ~40%
- Collaborated cross-functionally to deliver a seamless user experience for automated content generation
More Projects
Sentiment Analysis in Dravidian Languages
Detected homophobic and transphobic content in over 3,000 Tamil-English YouTube comments as part of Dravidian LangTech Workshop 2022.
Sentiment Analysis in Dravidian Languages
Detected homophobic and transphobic content in over 3,000 Tamil-English YouTube comments as part of Dravidian LangTech Workshop 2022. Conducted comparative study of ML models, ensemble models, and BiLSTM, with BiLSTM achieving the highest macro F1 score. The project involved preprocessing code-mixed text, handling Tamil script and transliterations, and developing robust models to identify harmful content in social media discussions. This work was part of a shared task focused on improving content moderation for underrepresented languages.
Multi-Class Image Classification
Designed custom CNN model in PyTorch for six-class malaria cell classification (5,000+ images) achieving 95% test accuracy.
Multi-Class Image Classification
Designed custom CNN model in PyTorch for six-class malaria cell classification (5,000+ images) achieving 95% test accuracy. Adapted ResNet-50 for transfer learning approach obtaining 92% accuracy. Optimized hyperparameters, reducing training loss by 80% for CNN and 58% for ResNet-50. The project involved extensive data augmentation techniques, batch normalization, and dropout regularization to prevent overfitting. Conducted detailed ablation studies comparing different architectures and training strategies. The high accuracy on unseen test data demonstrates the model's strong generalization capabilities for medical image analysis.
Information Retrieval Projects
Implemented the full modern IR stack from scratch: evaluation metrics, inverted indexes with compression, classical ranking models (VSM, BM25, QL), RM1/RM3 feedback, and more.
Information Retrieval Projects
Implemented the full modern IR stack from scratch: evaluation metrics, inverted indexes with compression, classical ranking models (VSM, BM25, QL), RM1/RM3 feedback, TextRank, TF-IDF K-means clustering, LambdaMART, and a dense dual-encoder with FAISS. Built efficient indexing structures using variable byte encoding and delta encoding for compression. Developed query expansion techniques using pseudo-relevance feedback. Implemented learning-to-rank models using gradient boosting. Created neural retrieval systems using BERT-based dense encoders and approximate nearest neighbor search with FAISS for fast similarity matching at scale.
Artificial Intelligence Projects
Built a Messenger Bot using AIML for keyword-based intent detection and a Career Expert System using Experta for personalized recommendations.
Artificial Intelligence Projects
Built a Messenger Bot using AIML for keyword-based intent detection to recommend food outlets and provide real-time weather updates via OpenWeatherMap API. The bot uses natural language processing patterns to understand user queries and responds with contextually relevant information. Developed a Career Expert System using the Experta Python library to generate personalized course and career recommendations based on GPA, publications, and achievements. The expert system uses rule-based reasoning to match student profiles with optimal career paths, considering factors like academic performance, research interests, and extracurricular activities.
Classification of Math Word Problems based on Difficulty
Performed multiclass classification of math word problems into different difficulty levels using Readability score, Math vocabulary, and problem length.
Classification of Math Word Problems based on Difficulty
Performed multiclass classification of math word problems into different difficulty levels (easy, medium, hard) using three attributes: Readability score, Math vocabulary, and problem length. Utilized Neural Networks (Keras Sequential model) with three dense layers, tanh and softmax activation, and Adam optimizer. Feature engineering involved computing readability scores, extracting mathematical terminology frequency, and normalizing problem lengths. The model achieved strong performance in distinguishing between difficulty levels, demonstrating the effectiveness of combining linguistic and mathematical features for automated problem difficulty assessment.
Mutual Book Exchange Portal
Built a web application using Spring Boot, Thymeleaf, and H2 database enabling registered users to exchange books for temporary use and return.
Mutual Book Exchange Portal
Built a web application using Spring Boot, Thymeleaf, and H2 database enabling registered users to exchange books for temporary use and return, with admin functionality as a 'super-user'. Designed 3 main features: publish/view/search book details for lending and borrowing, manage wallet transactions, and enforce penalties for late return. Implemented RESTful APIs for CRUD operations, JWT-based authentication, and role-based access control.
Microsoft Engage - Tic Tac Toe Game
Developed a Tic Tac Toe Game Web application using Minimax algorithm powered by AI with feature for playing with a friend.
Microsoft Engage - Tic Tac Toe Game
Developed a Tic Tac Toe Game Web application using Minimax algorithm powered by Artificial Intelligence with feature for playing with a friend. Used Javascript, Node.js, Bootstrap and deployed using Microsoft Azure. The AI uses the Minimax algorithm with alpha-beta pruning to calculate optimal moves, making it unbeatable when playing perfectly. Implemented two game modes: Player vs AI and Player vs Player. The application features a clean, responsive interface built with Bootstrap and real-time game state updates. Part of Microsoft Engage Mentorship Program 2020.
Python Game Development - Tetris
Built the Tetris game using pygame library in a 20-day workshop organized by The Girl Code.
Python Game Development - Tetris
Built the Tetris game using pygame library in a 20-day workshop organized by The Girl Code, a non-profit organization dedicated to empowering girls in STEM. Implemented core game mechanics including rotation with wall kicks, collision detection and line clearing with scoring system. Added features like next piece preview, score tracking, smooth animations and background music. The project demonstrated fundamental game development concepts including game loops, event processing, and state management using Object-Oriented Programming principles.
Interested in Collaboration?
I'm always open to discussing new projects, research opportunities, or technical challenges.