Resume

Summary

Software engineer with production full-stack experience from Stylabs Technologies and graduate work in machine learning, databases and distributed systems at the University of Georgia. My latest project, HomeSense, builds a streaming, web, mobile and Kubernetes platform around my thesis model for smart-home activity recognition. I have also built interactive learning tools for system design and machine learning, and I have a conference paper on smart-home activity recognition under review.

Selected projects

• Latest project

  HomeSense: a smart-home intelligence platform

  Independent project, built on my M.S. thesis model, June to October 2026

  My thesis model turned into a running platform: live Kafka streaming, anomaly detection with human review, a citation-checked assistant, a resident simulator, gated model releases, web and phone apps, and a Kubernetes deployment.

  • Designed and built a smart-home activity-recognition platform around my thesis model: FastAPI and PostgreSQL backend, Kafka event-time streaming, React web app, Expo phone app and a background worker.
  • Added anomaly detection with a human review loop, a citation-checked assistant, and a simulator in which a resident walks a real floor plan and ground truth is recorded.
  • Gated model releases behind measured promotion checks, shadow runs and review. Packaged the platform with Helm and verified recovery by killing pods on a local three-node Kubernetes cluster.
  • 27 architecture decision records, about 500 Python tests and 53 commits between June and October 2026.

  Stack: Python, FastAPI, PostgreSQL, Kafka, Redis, React 19, TypeScript, Expo, Kubernetes, Helm, PyTorch, MLflow.

• SystemForge: a system-design laboratory

  Independent project

  An interactive way to learn system design: instead of reading about caching, you flush the cache and watch the database fall over. A simulation engine drives 40 system labs, an architecture canvas, a code playground and scored challenges. It has helped over 10,000 users learn system design.

  Role: I designed and built the simulation engine, the 40 system labs, the canvas, the playground and the web app.

• MLForge: an interactive machine-learning lab

  Independent project

  A browser-only site that teaches machine learning by letting you change it: 75 lessons with live interactive labs and 20 guided end-to-end projects. Every model is written from scratch in TypeScript, so there is no server and nothing to install. It has helped over 5,000 users learn machine learning algorithms.

  Role: I designed and built the site, the lesson format and the from-scratch algorithms.

• Ringside: a watch-party app for live sports

  Independent project

  A watch-party app for people who follow sports together: spoiler-safe chat, live reaction counts, polls, pick'ems and a data desk with live tables and fixtures for UFC, F1, football, college football and cricket. A web app, a Node server and an Android app share one API. Around 200 users have used it.

  Role: I built the web app, the real-time server, the sports-data layer and the Android app.

• Multimodal smart-home activity recognition

  M.S. thesis, University of Georgia

  Sparse motion and door sensor logs turned into sequence, text, raster and graph views of the same event window, with the preprocessing, experiment and inspection tooling to evaluate them across four homes.

  Role: Thesis author. I built and ran the preprocessing, four-view pipeline, multimodal model, experiment tooling and evaluation described here.

• Profound Properties

  Team project at Stylabs Technologies, 2024

  A live Dubai real-estate platform for buying, renting and listing property, built by a small team on a tight timeline. I helped set up the foundation and built frontend components, backend integration, authentication and data workflows.

  Role: Full-stack contributor. I helped set up the project foundation (framework choice, template conversion, backend with authentication), built several components from scratch, wrote documentation and prepared the database with realistic data. The AI-assisted seeding covered 5K records and reduced manual curation by 40 hours, which helped deliver the project 12 days early.

• Manzil

  Professional work at Stylabs Technologies, 2023 to 2024

  A live product for design-led holiday homes and service apartments in Dubai, for daily and monthly stays. I built the chat support system for customers, employees and owners, and contributed rental, sales and expense features.

  Role: Full-stack contributor. I developed the chat support system for customers, employees and owners, and contributed features for rentals, sales and expense management.

• Hireavilla

  Professional work at Stylabs Technologies, 2023 to 2024

  A live product for renting luxury villas and holiday homes in India, searchable by location, dates and guests. A sister product to Manzil, where I worked on the same chat support system and rental, sales and expense features.

  Role: Full-stack contributor. I developed the chat support system for customers, employees and owners, and contributed features for rentals, sales and expense management.

• The Mainstreet Marketplace

  Professional work at Stylabs Technologies, 2023 to 2024

  A live online marketplace for sneakers, streetwear, apparel, watches and more. I developed components, fixed bugs, built API integrations, tested the application and wrote API documentation for the frontend and mobile teams.

  Role: Full-stack contributor. I developed components and API integrations, fixed bugs, tested features and wrote the API documentation, which improved user engagement by 27%.

• Distributed key-value naming service

  Coursework, Distributed Computing Systems (University of Georgia)

  A Java hash-ring naming service: a bootstrap server and name servers that look up, insert and delete keys, and rebalance key ranges as servers join and leave.

  Role: I wrote the bootstrap server and the name server for the course, individually.

Experience

• Developed new frontend components and integrated them with Node.js and Express APIs.
• Wrote API calls and MongoDB aggregate queries for data-heavy screens, and wrote API documentation used by frontend and mobile developers.
• Developed the chat support system for customers, employees and owners in the Manzil and Hirevilla rental marketplaces.
• Tested features, triaged bugs and fixed them across the client and server. Improved the marketplace's average page-load time from 4 s to 1 s with code splitting, lazy loading and component optimization.
• Built 40+ MongoDB aggregation pipelines over 50K+ user and transaction records, reducing average query latency from 750 ms to 35 ms.
• Shipped 35+ production features across 4 web applications serving 50K+ users.
• Helped set up the Profound Properties platform: framework choice, template conversion, authentication and data seeding.

Education

• M.S. Computer Science (thesis track), University of Georgia

  Expected December 2026

  • Thesis: Multimodal Self-Supervised Activity Recognition on CASAS Smart-Home Sensor Streams, advised by Fei Dou.
  • GPA 3.57/4.0.
  • Coursework: Algorithms, Distributed Computing Systems, Database Management Systems, Computer Networks, Machine Learning in IoT.

• B.E. Computer Engineering, Savitribai Phule Pune University (ISBM College of Engineering)

  2019 to 2023

  • First Class with Distinction.
  • GPA 8.7/10.
  • Coursework: Data Structures and Algorithms, Design and Analysis of Algorithms, Theory of Computation, Discrete Mathematics, Database Management Systems, Computer Networks and Security, Systems Programming and Operating Systems, Cloud Computing, High Performance Computing, Internet of Things and Embedded Systems, Artificial Intelligence, Machine Learning, Deep Learning, Data Science and Big Data Analytics, Software Engineering, Web Technology, Software Testing and Quality Assurance.

Research and writing

• Multimodal Self-Supervised Activity Recognition on CASAS Smart-Home Sensor Streams

  M.S. thesis, University of Georgia

• FACET: Factorized Ambient-Sensor Experts with Local Competence-Weighted Fusion for Smart-Home Activity Recognition

  Conference paper, submitted and under review (joint work)

• Survey on Contrastive Self-Supervised Learning in Human Activity Recognition

  Graduate research seminar, University of Georgia

• Resume Ranking System Using Machine Learning & NLP

  International Journal of Scientific Research in Engineering and Management (IJSREM), Vol. 07, Issue 05, May 2023

Skills

Languages

Python, TypeScript, JavaScript, Java, C, SQL

Frontend

React, Expo (React Native), Next.js, Vue 2/3, Nuxt.js, Nuxt UI, Vite, KaTeX, HTML, CSS, Material UI

Backend and data

FastAPI, Node.js, Express, Flask, REST APIs, Socket.IO, PostgreSQL, MongoDB, MySQL, Redis, Kafka, Drizzle ORM

Systems and networking

TCP and UDP sockets, Threads and locks, DNS and HTTP range requests, OpenSSL, Consistent hashing, Discrete-event simulation

Infrastructure

AWS, Docker, Docker Compose, Kubernetes, Helm, MLflow

Machine learning

PyTorch, PyTorch Geometric, TensorFlow, NumPy, scikit-learn, pandas, matplotlib, Transformers, CNNs, Graph neural networks, Self-supervised and contrastive learning, Federated learning, Denoising autoencoders, NLP, RAG, LangChain

Algorithms and databases

Dynamic programming, Hidden Markov models, Hash indexing, Query optimization, Relational algebra

Testing and tools

Vitest, Playwright, Git, Linux