I'm a Machine Learning and Artificial Intelligence enthusiast with a proven track record in developing innovative AI solutions and optimizing system efficiency in industry and research settings. Currently interning in a dynamic ML role where I apply automation and advanced pattern recognition techniques, achieving measurable improvements in workflow efficiency. As a Research Assistant at UC Davis, I led the design and deployment of a cutting-edge TinyML project, achieving high accuracy for ECG signal classification and significantly enhancing device efficiency for wearable technology. With a diverse portfolio of projects and strong technical skills in Python, SQL, Next.js, and AWS, I am passionate about harnessing AI to drive meaningful outcomes and advance solutions in real-world applications. I am eager to contribute my expertise and innovative approach to the fast-evolving tech landscape.
- π Iβm currently working on InvestIQ AI, an AI-driven personal finance web application that offers predictive financial analysis.
- π± Iβm learning Rust, Deep Learning, Qiskit and Horse Riding
- π― Iβm looking to collaborate on AI, machine learning, and finance tech projects.
- π¬ Ask me about Quantum Computing
- π« How to reach me: vsxpatel@ucdavis.edu
-
Software Engineering Intern, Drevol (Oct 2024 β Present)
- Developed automation solutions in C# and .NET, optimizing core processes for a 20% efficiency boost.
- Implemented pattern recognition tools to improve system reliability, reducing bottlenecks by 30%.
- Deployed ML-driven tools on Azure DevOps, enhancing project tracking accuracy by 15%.
-
Machine Learning Research Assistant, UC Davis (Feb 2024 β Present)
- Engineered low-power algorithms for ECG classification, achieving 92.8% accuracy.
- Applied SHAP and LIME techniques for Deep Neural Network optimization, boosting accuracy by 7%.
-
InvestIQ AI | Next.js, TailwindCSS, Vercel, NLP
- Developed a predictive finance app with 90% accuracy, helping users optimize their portfolio performance by up to 15%.
- Integrated an intelligent chatbot with a 95% query resolution rate and data visualizations that cut decision-making time by 30%.
-
Scream Detection System | Python, MLP, Deep Learning, React
- Designed a deep neural network to detect distress calls, achieving 93% accuracy by distinguishing acoustic differences.