About Me
I'm a passionate and detail-oriented Fullstack Software Engineer with a strong foundation in computer science and hands-on experience in full-stack development, automation, and cloud-based systems. With a Master's degree in Computer Science and real-world experience across startups and internships, I enjoy solving complex problems through clean, efficient code and collaborative teamwork.
I specialize in Python, JavaScript, and modern frameworks like React and Node.js, and I'm constantly exploring new technologies from machine learning to DevOps to stay ahead in this fast moving field. Whether it's building scalable backend systems or crafting user friendly frontend interfaces, I aim to create software that makes a real impact.
Experience
Find Me LLC
Fullstack Developer Intern
Dec 2024 – Present | Remote
- Led a team of 12 engineers to build scalable and extensible microservices aligned with platform reliability goals
- Designed and deployed RESTful APIs and GraphQL endpoints to support modular backend services and improve data integration
- Developed typo-tolerant search using fuzzy logic, enhancing user discoverability and reducing bounce rate
- Improved backend performance by optimizing API response time, achieving significant latency reduction
- Integrated fault-tolerant data layers with PostgreSQL, MongoDB, and Redis
- Built centralized observability infrastructure using OpenTelemetry, Promtail, and Grafana Loki for real-time monitoring
- Implemented secure, scalable OAuth2/JWT authentication, following modern software engineering best practices
- Deployed production-grade pipelines with GitLab CI/CD, enhancing delivery speed and system reliability
Education
Boston University
Master of Science in Computer Science
Sep 2022 – May 2024 | Boston, MA
- Focused on Artificial Intelligence, Machine Learning, Cloud Computing, and Distributed Systems
Savitribai Phule Pune University
Bachelor of Engineering in Computer Engineering
Aug 2017 – Jun 2021 | Pune, India
- Capstone: E-Health Patient Management System which uses Voice Recognition and Machine Learning to predict diseases based on symptoms.
Research & Publications
An E-Health Patient Management System.
Grenze International Journal of Engineering & Technology (GIJET) · 2021 · Vol 7 · Issue 2 · Page 41-46
View Paper
- Voice-Based Patient Interaction: The system enables patients to describe their symptoms via voice, which is transcribed using speech recognition and processed using Natural Language Processing (NLP) to extract relevant medical information.
- Disease Prediction Using Machine Learning: Extracted symptoms are analyzed using a Random Forest algorithm, achieving a prediction accuracy of 93.55% across 41 diseases, using a dataset of 4920 records.
- System Components and Technologies: The architecture integrates speech-to-text processing using Mel Frequency Cepstral Coefficients (MFCC), NLP for symptom extraction, and a web-based interface for remote consultation and record management.
- Future Scope: Plans include incorporating medicine recommendations, multilingual support for local languages, and building a complete electronic medical records system for improved accessibility and long-term care.
Proposed Model of Speech Recognition using MFCC and DNN
International Journal of Engineering Research & Technology (IJERT) · May 10, 2020
View Paper
- Proposed a speech-to-text system that combines pre-processing (using Polygon Smoothing Algorithm), feature extraction (using MFCC), and classification (using Deep Neural Networks), aiming to enhance recognition accuracy especially for large datasets.
- The Mel Frequency Cepstral Coefficients (MFCC) technique is employed to capture key speech features such as pitch and power, making it well-suited for modeling human auditory perception in speech recognition tasks.
- A comparative study demonstrates that while SVM is effective for smaller datasets, DNNs provide superior accuracy and scalability for large-scale speech recognition due to their deep learning capabilities and universal approximation properties.
- The model holds promise for voice-based applications in multilingual systems, biometric authentication, assistive technologies for disabled individuals, voice-controlled games, and military-grade speech recognition systems.
Projects
Travel Genie
A travel planning assistant that uses AI to provide personalized recommendations based on user preferences and travel history.
Fynd Me
A shelf recognition system that uses computer vision and machine learning to identify and recognize shelves in images.
Hey Gen
A utility library that implements a polling mechanism to check the status of asynchronous jobs.
Trade Pulse
TradePulse uses advanced machine learning to analyze stock trends and predict market movements. Get real-time insights, risk assessments, and custom alerts to make informed trading decisions. 🚀
Contact
Feel free to reach out to me with any questions or opportunities. Fill out the form below and it will open your default email client.