Dr. Aqib Rashid

I look for people who are genuinely curious about the problem and not just the technology, the machine learning frameworks and the actual languages and just different engineering tools, so to speak.

You require that curiosity in order to be able to solve difficult problems.

You want people who are eager to learn, but also eager to contribute at the same time.

And you want people who hold themselves to a very high standard.

That's why looking for the people who have, of course, the engineering prowess and the domain knowledge is absolutely vital.

But also looking for people who are genuinely curious, as we did at GlassWall, is imperative when you're trying to solve a very difficult problem, as we have done with Foresight and with this product that can detect malware.

When I joined the company, there wasn't really an ML pipeline or an AI pipeline that had been used for experimentation and building models because up until that point, a lot of the work was in the research phase and proving out the feasibility of training models with CDR telemetry.

So when I joined, one of the first things that we did was build our ML pipeline from the ground up.

So that involved a lot of AI engineering and a lot of discussion and thought around scalability.

And I'm pleased to say that maybe two years later or so, we're still using that ML pipeline.

We're still using that technology that we built.

that can, like I say, ingest millions and millions of files and conduct feature analysis, conduct feature selection, conduct model training, do all the post-training activities, and at the end of it, give you a model in a matter of hours for the file types that we care about.

And being able to do this is no easy feat, especially when you consider the costs that could be involved in doing so.

We've got the costs down quite considerably as well.

But the ultimate beauty of all this of course is that we have models that will stand the test of time and they will scale with the evolving threats and with evolving malware as time goes by.

So it wasn't the case that we were fighting with scalability or fighting necessarily as we grew.

We knew ahead of time that we want to make this process of developing machine learning and AI models as repeatable, as automatable, as reproducible as possible.

while also ensuring that there is going to be a high quality model at the end of this entire process as well and this is just on the training and the ml side so one could also consider scalability in terms of using the model at inference time so that is

Deploying the model and giving it to a customer and letting them have a go of it and take it for a drive.

It's important that at inference time as well or at prediction time, the model behaves reliably and it scales well there as well.