Using her passion for math and science to work for change

What first sparked your interest in engineering?

I was one of those kids who knew from a very young age that I wanted to be an engineer. My father is an engineer, and his father was an engineer, so I was introduced early on to what engineering is all about. 

An engineer is someone who brings science into the real world—when you graduate from UBC engineering, you actually get a degree in applied science. It’s a career that enables you to use your passion for math and science to work for change outside the lab, in the communities where we live. 

Looking back, what were some highlights of your undergraduate education?

My five years at UBC were extremely formative. In my courses, I learned how to do challenging things in teams, which wasn’t a skill I had going in. 

I remember countless evenings and late nights in study rooms, whiteboarding with my peers.

I was quite active with Engineers Without Borders (EWB) for three or four years. EWB taught me to think about engineering in new ways and deepened my understanding that many of the world’s biggest challenges aren’t just technical. It is so important to develop communication skills and to be able to compassionately translate existing technology into real-world solutions that people actually need. 

Can you describe your current role at Floodbase?

I’m a staff machine learning engineer at Floodbase, where I’ve been for over four years. Floodbase creates near real-time flood maps by combining satellite sensor observations, physical models and state-of-the-art computer vision techniques. This data is used to structure parametric insurance policies and trigger payouts. Flooding is the most common natural disaster, and over 80% of economic losses globally are uninsured. Parametric insurance is a way to get immediate payouts if a disaster reaches a certain threshold, unlike traditional insurance, where payouts can be slow and complicated. 

My role is to build the models that process satellite and sensor data to generate real-time flood estimates that can be used to assess risk and structure insurance policies. 

How did your background prepare you for this position?

In grad school, I focused on computer vision and machine learning methods to segment and detect lesions in MRI scans. After grad school, I worked for several years at a startup in Montreal called Imagia Cybernetics, a med tech company focused on medical imaging research. I worked on identifying pathology in various scans—MRI, CT, lung and eye data. 

While that seems different from flood mapping, both involve processing large, complex datasets—whether medical images or satellite data. The skills I developed to analyze rich data and build models directly apply to my current work.