Arvind Boominathan

MS Graduate

Lakehead University · 2025

About

MS graduate now in Toronto —
building data systems that scale.

I'm transitioning into data engineering and data science, based in Scarborough, Toronto. My background spans distributed data pipelines on Spark + Hadoop, cloud deployments on AWS and GCP, ML model development, and full-stack applications. I bring research rigour to production problems.

My MS thesis at Lakehead University built deep learning pipelines fusing multi-omics data — gene expression, DNA methylation, copy number variation — to predict cancer subtypes. That kind of large-scale, heterogeneous data wrangling is exactly what data engineering demands.

Projects shipped

97%

Chatbot accuracy

Languages supported

553m

Personal record height

Core Skills

Apache Spark / Hadoop92%

Python / ML (TF, PyTorch)90%

SQL / MongoDB / Firebase88%

AWS / GCP / Docker80%

Flask / React / Node.js75%

Java / C / C++72%

Journey

2025 — Present

Data Engineer · Job Seeker

Scarborough, Toronto · GTA

Actively seeking data engineering and data science roles. Building projects, teaching coding, and contributing to open source.

2023 — 2025

M.Sc. Computer Science

Lakehead University · Thunder Bay, ON

Thesis: deep learning pipelines fusing multi-omics data (gene expression, DNA methylation, CNV) for cancer subtype prediction via Graph Attention Networks.

2023

GDSC Hackathon Finalist · Guest Speaker

Lakehead University · Kumizhi High School, TN

Reached finals at Google Developer Student Club Hackathon. Spoke at a government school career event in Tamil Nadu.

2019 — 2023

B.Tech Computer Science & Engineering

Vellore Institute of Technology · Chennai, India

Built the multilingual telehealth chatbot and early full-stack projects. Developed a strong foundation in algorithms, ML, and systems programming.

Work

Selected Projects
& Research

Thesis

Multi-omics Cancer Analysis via Deep Learning

Integrating gene expression, DNA methylation, and copy number alteration through Deep Multiset CCA and Graph Attention Networks to build a shared latent space — improving breast and bladder cancer subtype prediction and biomarker identification. A large-scale heterogeneous data problem at its core.

Graph Attention Networks Deep MCCA PyTorch Multi-omics Data Python

GitHub

001

QuickEval — AI Assignment Grader

Web platform using Flask + Firebase where NLP (BERT embeddings + cosine similarity) auto-grades submitted PDFs on keyword relevance, semantic match, plagiarism, and punctuality. Built for real classroom use.

BERTFlaskFirebaseNLP

In Progress

002

Multilingual Telehealth Chatbot

97% accurate disease diagnosis chatbot processing symptoms in five Indian languages. Ensemble of 10 ML classifiers, designed specifically for underserved rural communities without English access to healthcare.

ML EnsembleNLPFlaskHealthcare

Private

003

YouTube Trending Analysis — Data Pipeline on Spark

End-to-end data engineering pipeline ingesting, transforming, and analysing YouTube trending data at scale. Built on a Hadoop cluster with Spark for distributed processing — covering ingestion, transformation, aggregation, and insight extraction from millions of records.

Apache SparkHadoopPythonETLData Pipeline

GitHub

004

Railway Track Fault Detection

CNN-powered infrastructure safety system using high-resolution image analysis to detect track faults. Targets railways where manual inspection is dangerous or impossible at scale.

CNNComputer VisionPython

GitHub

005

GDSC Hackathon Finalist · Guest Speaker

Reached the finals of Google Developer Student Club Hackathon at Lakehead, 2023. Also spoke at a career guidance programme at a government high school in Kumizhi, Tamil Nadu — giving back to where it started.

🏆 GDSC 2023🎤 Community

Beyond the Lab

"Some people debug code.
I debug code and then
walk off a tower."

That photo on the right? That's the CN Tower EdgeWalk — 553 metres above Toronto, harness clipped, arms out, peace sign up. It's not a metaphor. It's just a Tuesday.

From Chennai, India — now living in Scarborough, Toronto

Passionate about healthcare access — built a chatbot for rural India

Guest speaker at govt. schools, because every kid deserves to see what's possible

Open to work in data engineering, data science, and ML roles across the GTA

Selected Projects& Research

Let's BuildSomething Real

Arvind
Boominathan

Selected Projects
& Research

Let's Build
Something Real