Dhruv Shah
I build reproducible data pipelines, machine-learning systems, and automation tools for scientific and operational data, with a particular interest in bioinformatics, genomics, and dependable software infrastructure.
FocusBioinformatics and genomics
EngineeringReliable pipelines and automation
MethodsScientific computing and machine learning
01 / Selected work
Selected work combining biological data, reproducible analysis, machine learning, and dependable data engineering.
Single-cell bioinformatics
01An end-to-end single-cell RNA-seq workflow that processed 50 GB of raw sequencing data from approximately 120,000 cells in under two hours.
Implemented quality-control and normalization steps that recovered the expected transition from stem cells toward heart-muscle cells across day 0 to day 16 samples.
Genomics and machine learning
02A Transformer-based classifier for human, bacterial, viral, and fungal genomic sequences, trained on a custom Biopython encoding pipeline.
Reached 75% classification accuracy and paired the model with a SQL schema for efficient sequence storage and retrieval.
Reproducible data analysis
03A Python event-study pipeline that joined Formula 1 race results with market data across 778 sponsor-race observations.
Estimated sub-0.5% next-day movement and near-zero three-day reaction after controlling for sponsor and race fixed effects.
02 / Venture
CancerSync is an early-stage venture exploring how genomic data can become clearer, more actionable, and more useful at the point of care.
Early-stage venture
A platform concept for turning tumor genomics into actionable clinical insight.
View CancerSyncMission
We are at the early stages of building a platform that will provide oncologists with actionable insights, enabling personalized treatment plans based on the unique genetic profile of each patient’s tumor. Our mission is to improve patient outcomes and push the boundaries of personalized medicine.
What we are working toward
03 / Experience
Production software and data automation work across energy, enterprise systems, and financial operations.
Sep 2025 — Feb 2026
Independent Electricity System Operator (IESO)
Built data-analysis and workflow-automation systems for operational and contractual electricity-market processes.
Jan–Apr 2024; Jan–Apr 2025
KORE Solutions
Improved the performance, correctness, and test reliability of production enterprise software and data workflows.
Jan 2023 — Apr 2023
HTS
Automated finance operations and reporting with Python, JavaScript, Selenium, and data-visualization tools.
04 / About
I am interested in the engineering layer behind scientific discovery: the pipelines, interfaces, validation rules, and data systems that determine whether an analysis is trustworthy, reproducible, and useful.
My combined computer science and business education helps me connect implementation details with research goals, operational constraints, and measurable outcomes.
Education
Bachelor of Computer Science
Computer science, algorithms, software systems, data, and scientific programming.
Bachelor of Business Administration
Business analysis, finance, strategy, operations, and product thinking.
05 / Technical skills
A practical stack for scientific analysis, bioinformatics workflows, automation, and reliable software delivery.