About
A software engineer who moved from product work into research without leaving the engineering behind.
How I got here
I studied Computer Engineering at Savitribai Phule Pune University (ISBM College of Engineering). My final-year project was a resume ranking system built with machine learning and NLP: I led the team, wrote the Flask server and React client around the model, and we published a technical paper about it.
From May 2023 I worked at Stylabs Technologies as a technical intern on production web applications. I developed frontend components and integrated them with Node.js and Express APIs, wrote MongoDB aggregate queries, documented APIs, and fixed bugs across the stack. On Profound Properties I helped set up the project from the start.
I then joined the University of Georgia for an M.S. in Computer Science. Coursework in distributed computing, databases, networks and machine learning gave me the systems side, and my thesis puts it together with research on smart-home activity recognition.
Between June and October 2026 I built HomeSense, a platform around the thesis model: Kafka streaming, a FastAPI backend, web and phone apps, anomaly review, a resident simulator, gated model releases and a Kubernetes deployment. It is the clearest picture of how I work on a whole system.
Read the HomeSense case studyRead the thesis case studyRead the Profound Properties case study
How I work
I treat evaluation as part of the design.
In my thesis every model sees the same windows and the same splits, and each result is reported with its metric, seeds and setting rather than as one headline number.
I build tools to look at the data.
A playback simulator and a sensor annotation tool let me check coordinates, windows and labels before trusting a score.
I write things down.
At Stylabs I wrote API documentation so frontend and mobile developers could work in parallel, and documented the components I built.
Research and writing
Thesis
Multimodal Self-Supervised Activity Recognition on CASAS Smart-Home Sensor Streams
M.S. thesis, University of Georgia
Four derived views of sensor windows, evaluated on four CASAS houses.
Paper under review
FACET: Factorized Ambient-Sensor Experts with Local Competence-Weighted Fusion for Smart-Home Activity Recognition
Conference paper, submitted and under review (joint work)
Not yet accepted or published.
Survey
Survey on Contrastive Self-Supervised Learning in Human Activity Recognition
Graduate research seminar, University of Georgia
Sole-authored, ACM-style survey of contrastive approaches (SimCLR, CPC, multi-sensor fusion, time-frequency contrast) and open problems such as false-negative handling and augmentation design.
Technical paper
Resume Ranking System Using Machine Learning & NLP
International Journal of Scientific Research in Engineering and Management (IJSREM), Vol. 07, Issue 05, May 2023
Written with the undergraduate project team.
I also volunteered at the University of Georgia School of Computing 2025 Research Day, where I compiled the book of abstracts for the research seminars and papers on display.
Elsewhere
Based in Athens, Georgia. GitHub(opens in a new tab) and LinkedIn(opens in a new tab) have more.