Driven MS Computer Science student at Arizona State University (GPA 4.0, Dec 2025 Expected) with a strong foundation in AI/ML and over two years of professional experience as a Software Engineer at LTIMindtree. There, I spearheaded a migration of 1M+ customer records to Oracle Fusion Cloud, achieving an estimated 15-20% reduction in operational costs, and developed automation tools saving 300+ engineering hours per cycle.
My academic and research pursuits include engineering deep learning pipelines for computer vision (94% accuracy in particle tracking) and developing impactful AI applications. I am passionate about leveraging data and cutting-edge technologies like LLMs, PyTorch, and AWS to build scalable, intelligent systems that solve real-world problems.
I am actively seeking Summer and Fall 2025 Internship opportunities where I can contribute to innovative Software Engineering or Machine Learning Engineering projects, applying my expertise in building and deploying data-driven solutions.
Engineered a PyTorch/YOLOv8/OpenCV deep learning pipeline detecting & tracking 3.4K+ particles/frame (94% accuracy) for soil analysis, reducing analysis time by 70%. Scaled this automated system, achieving >3x analysis efficiency to directly support critical infrastructure safety by enabling complex geotechnical simulations of soil behavior under bridge loads.
Focusing on AI/ML, Cloud Computing, and Big Data. Key coursework includes Statistical Machine Learning, Data Processing at Scale, and Data Mining, providing a strong theoretical and practical foundation for developing intelligent systems. Expected graduation: Dec 2025.
Led migration of 1M+ customer records to Oracle Fusion Cloud (SQL, Python, APIs), achieving an est. 15-20% operational cost reduction and enhancing data scalability/security. Developed an Angular/Node.js configuration tool, automating environment transfers and saving 300+ engineering hours/cycle. Optimized 100+ SQL queries, cutting average execution time 25%. Implemented automated testing (JUnit/PyTest) for 75+ critical tasks, reducing validation errors by an est. 30-35%.
Built a strong foundation in computer science fundamentals, including Data Structures & Algorithms, Object-Oriented Programming, and Database Management Systems, complemented by early explorations into Machine Learning.
Engineered an LLM-powered system that enables non-technical users to query databases using natural language, eliminating the typical 2-4 weeks of SQL training. Fine-tuned a T5 model on the Spider dataset, achieving 90% execution accuracy and 99%+ syntactic correctness, with robust generalization to 100+ unseen database schemas.
Built a system to predict and summarize individual personalities from 1M+ survey responses, using ensemble ML models for trait prediction (78% accuracy with CatBoost) and LLMs for human-readable insights. Clustered responses into 5 distinct profiles using PCA and K-means to guide LLM-generated summaries.
Engineered a serverless video analysis system that automated key frame extraction and face recognition, reducing manual effort by 65% and cutting cloud compute costs by 40–50%. Delivered 90%+ real-time face recognition accuracy using an AWS Lambda–powered OpenCV pipeline with ResNet-34, validated on 100+ unseen video samples.
Built an Android app to combat information overload by filtering messages based on user interests, saving users an estimated 30–35 minutes daily. Published research validated the solution, achieving 96% filtering accuracy on 11K+ messages using NLP with SVM, Naive Bayes, and Logistic Regression models.
