About

I’m Arijit Dey, a machine learning engineer/researcher focusing on multimodal (vision-language) learning, graph ML, and optimization.

What I do

• AI Health Analytics (Symviq, Aug 2024–present): building vision-language models for chronic disease classification using retinal fundus images and designing foundation-model style encoders for downstream medical imaging tasks.
• Research + engineering: I enjoy working end-to-end—from problem formulation and modeling, to training infrastructure, evaluation, and clean open-source code.

Technical strengths

• Deep learning: contrastive learning (CLIP/SimCLR), vision-language models, generative modeling (GANs), transformers
• Graph ML: GCN/GAT-style architectures, pooling, graph classification pipelines
• Optimization: convex optimization, stochastic/delayed/asynchronous optimization, stability and convergence intuition

Education

• MS, Electrical & Computer Engineering (UCLA) — 2023–2024
• M.Tech, Electrical Engineering (IISc) — 2021–2023
• B.E., Instrumentation & Electronics Engineering (Jadavpur University) — 2017–2021

Coursework I’ve leaned on most

• UCLA: Convex Optimization, Neural Networks and Deep Learning, Advanced Neural Networks and Deep Learning, Decision Making in Stochastic Processes
• IISc: Random Processes, Linear Algebra, Pattern Recognition and Neural Networks, Advanced Deep Representation Learning

For a detailed timeline and full project list, see CV and Projects.