Jason Chalom

Principal Software Engineer, Computer Scientist, 3D Printing Enthusiast, and Gamer
I build. I make. I code.

About Me

I am a Computer Scientist, principal software engineer, and gamer
I have a master's degree specialising in explainable AI in computer vision from the University of the Witwatersrand.

I am a dedicated and hard worker who is not afraid of a challenge and who does not give up easily. I love building cool things with computers.

None of the views I expressed here (and on my blog) are that of my Employer's.

The theme for this site is a modified version of Grayscale

My Skills and Experience

I have worked for over 12 years in software engineering building features, performing DevOps and infrastructure work and helping with security compliance work like framework upgrades. From the research side I have experience building AI systems for vision work, prediction and natural language processing. I have a deep love of computer science and always want to push myself to learn new things. Previously I have experience in the IT space maintaining compute nodes and servers, as well as securing them.


I have professionally been a Ruby on Rails developer for the last decade but also have experience in .NET, Python, NodeJS and other stacks.

Presentations & Talks

A timeline of presentations and talks I've given over the years

July 2025

IndabaX 2025 South Africa

Building out a sustainable and production ready AI software solution

November 2024

University of the Witwatersrand - Innovation Day

Poster: Attribution Methods for Explaining Deep Models for Self-Driving Cars (Masters by dissertation)

July 2024

IndabaX 2024 South Africa

GradSUM: A Method to Quantitatively Characterise and Explain Deep Learning Model Behaviour
+ Flash Presentation: AI Benchmark Toolkit

October 2023

University of the Witwatersrand, RAIL Lab

Explaining Transformer Models (From a Vision perspective)

2022

AI Expo Africa & IndabaX South Africa

Poster: A Tool-kit Of Techniques To Make Computer Vision Models Easier To Train And Evaluate
+ The Application of Attribution Methods to Explain an End-To-End Model For Self-Driving Cars

July 2021

University of the Witwatersrand, PRIME Lab

An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale - An Overview

June 2020

University of the Witwatersrand, RAIL Lab

Mini-Survey of Attribution Methods

February 2020

Tech Folk Meetup Johannesburg

My code is slow, and why you should care: Musings of a software developer

December 2019

University of the Witwatersrand, RAIL Lab

Fun Talk: Why do Robots Fallover?

June 2019

University of the Witwatersrand, RAIL Lab

My Cross-Sectional Investigation for Autonomous Vehicle Research

My Blog

Visit My Blog

Contact Me

Feel free to email me to provide some feedback,
give me suggestions on my projects, or to just say hello!

[email protected]