Turns half-baked ideas into things that actually work.
Software engineer at BNY and an IIT Bombay graduate, with a major in
Chemical Engineering and a minor in Computer Science & Engineering. I build
backend systems, work with AI, and take on problems that don’t always have
an obvious answer — from scalable systems to machine learning. Outside
work, I’m building side projects, learning how things work under the hood,
and wondering why the “small fix” took three hours.
Now
Software engineer· BNY, since Aug 2025
Studied
IIT Bombay· B.Tech. in Chemical Engineering, Minor in Computer Science and Engineering
二 Projects
Featured
Haemoglobin estimation using multimodal deep learning
Semester-long R&D project · Prof. Nirmal Punjabi · 2025
Estimates blood haemoglobin from photos of the conjunctiva, palm, fingernail and tongue, together with age, sex and BMI.
Challenge
Most of each photo is not tissue, so reconstruction losses were masked to make the encoders learn from tissue regions rather than the frame.
Approach
Trained 4 attention-based variational autoencoders, 100 epochs each on 128 × 128 images, fused their features with age, sex and BMI into a 1,056-dimensional input, and compared 6 input configurations. A ResNet18–GATv2 graph model then linked 16 image-patch locations with the patient data.
Outcome
The graph model reached a test MAE of 1.3576 and RMSE of 1.7283. Across the 6 configurations, tabular data alone was the strongest single input (1.4448 MAE) and fingernails the strongest image (1.7640 MAE).
Python
PyTorch
VAEs
GATv2
Few-shot oral lesion classification
Semester-long R&D project · Prof. Nirmal Punjabi · 2024
Classifies 6 types of oral lesion from photos, learning from only a few labelled examples per class.
With too few labelled images for a conventional classifier, used a prototypical network evaluated in episodes, and masked each lesion to its annotated polygon so the model saw the lesion rather than the tissue around it.
55.54% accuracy and 0.5568 macro F1 across 6 classes, against 16.7% chance
Python
OpenCV
Prototypical networks
Flight booking microservice
Self project · 2024
A flight booking backend split into Express microservices for flight search, booking, email reminders and auth.
Seat counts live in the flight service and bookings in another, so a booking starts In Process, checks and decrements seats through the flight service’s API, and is marked Booked only after that succeeds.
Node.js
Express
MySQL
Sequelize
Don’t let labels define you
Course project · Prof. Abir De · 2024
Clusters 114,000 Spotify tracks into synthetic genres and measures how closely they line up with the real ones.
There is no ground truth for a synthetic genre, so the number of clusters was chosen with AIC, BIC and the elbow method, and the result checked against real genres with frequency plots and cosine similarity.
110 synthetic genres identified across 114,000 tracks
Python
Gaussian mixture models
AIC/BIC model selection
Hierarchical few-shot generative models
Course project · Prof. P. Balamurugan · 2023
Trains hierarchical generative models that produce new samples of a class from only a few examples, on the double MNIST dataset.
Generating from only a few examples per set means the model has to infer what the set has in common; implemented the hierarchical model in PyTorch and analysed how its latent variables affect few-shot generation on double MNIST.
Python
PyTorch
Latent variable models
三 Experience
– present
BNY· Software engineer
Ship full-stack features end to end for a client-facing portal on Spring Boot microservices and Angular, including API design, an Angular monorepo migration and security vulnerability fixes.
Helped build developer tooling for other teams: an app generator that scaffolds a deploy-ready application, and a RAG-based assistant that answers engineers’ everyday setup questions and common problems.
–
BNY· Software engineering intern
Localised an Angular app into English and German with a separate build per locale, served by server-side redirection on a cookie value so no server configuration had to change.
Wrote prebuild and postbuild scripts that generate the locale files automatically and stop browsers serving a stale locale from cache.
–
Indian Institute of Technology Bombay· Minor in Computer Science and Engineering
Coursework in data structures and algorithms, design and analysis of algorithms, computer networks, machine learning and deep learning.
–
Indian Institute of Technology Bombay· B.Tech. in Chemical Engineering
CPI 8.12/10
AP grade in Computational Methods Lab, top 2 of 169
JEE Main 99.72 percentile (maths 100); JEE Advanced 97.20 percentile