Hey there!
My name is Tirth Shah, I'm currently a Data Engineer at theScore and a recent graduate from the University of Toronto (U of T). I've started these blogs in an attempt to share some of my findings, learnings and career advice (specifically for New Grads).
Feel free to share any of my articles with your friends and peers!
Understanding Batch Ingestion Using Data Engineering
Tips and Tricks for Coding Interviews
January 30, 2021 - 8 min read
After doing over 40 interviews in a span of 5 years (4 internships + full time), I have gathered a set process on how to approach them.
In this article, I have included how I prepare for a coding interview, my step by step template on how to tackle a coding question and some common mistakes made.
Click on the button below to read my article.
Recognizing Private Content in an Image via Machine Learning Model
November 29, 2019 - 6 min read
During my undergrad, I had done some research and developed a CNN and a ResNet50 model to detect presence of private data (i.e. credit card digits, face reflections, prescription snippets) on images taken by visually impaired users in an attempt to prevent them from accidentally sharing such private content on social media platforms.
Click on button below to read my article which was published on Analytics Vidhya.
Intro to Deep Neural Networks
November 18, 2019 - 8 min read
Words like "AI", "Machine Learning" and "Deep Learning" are intimidating at first sight, but are quite simple once looked into in detail.
To help mitigate this fear, I have tried to compile key concepts into one article as an introduction to Deep Neural Networks. It is written for audience who has minimal or no knowledge in this field.
Click on button below to read my article which was published on Analytics Vidhya.
Getting Started with Apache Airflow
March 1, 2022 - 6 min read
In today’s world, the need of automation is at an all-time high. It allows us to use our allocated resources efficiently, improves quality and reduces human error.
Many tech-driven teams have a relatively common pipeline — collect data, preprocess it, upload it somewhere and generate a report. Apache Airflow is one of the tools that would be able to schedule, trigger and process in the order defined; all on its own, without any human interference.
Click on button below to read my article which was published on Dev Genius.
.png)