Sharing with you how to build a machine learning inference API using FastAPI

Hello there friends! We’re back again with another semi-quick post on creating a machine learning inference API with Docker and FastAPI. Truth be told, I actually wrote this post for me more than anything. While I am very familiar with Docker already, I personally have been using Flask to build my ML inference APIs in the past. Not that there’s anything necessarily wrong with Flask, but it seems like FastAPI is now quickly becoming the industry standard. Some of the benefits of FastAPI include…

  • Faster than Flask: Truth be told, I tried to demonstrate a speed test between Flask and…

A beginner’s guide for where to start your data science learning journey!

At least twice a week, I’m approached by technical and non-technical folks alike asking my thoughts on where to begin learning about data science and machine learning. The reason folks reach out to me is because I have a very unconventional background. In a nutshell, I pivoted from a purely business career path with little technical knowledge to becoming a full blown machine learning engineer with the assistance of non-traditional educational resources. (Non-traditional = I didn’t get a formal degree in this.)

Toward the beginning of 2020, I wrote an extremely robust guide sharing every little thing I did, but…

Terraform + SageMaker

Helping to get you started with creating resources on AWS SageMaker using Terraform

Hello there, folks! Today, we’re starting a new series on using Terraform to create resources on AWS SageMaker. I expect you’re likely familiar with what SageMaker is, even if only on a very general level. In a nutshell, SageMaker is AWS’s machine learning service. AWS has poured a lot of energy into this particular service over the years, obviously in response to the explosive growth that the data science / machine learning practice has become across all industries. It’s sort of difficult to keep up with the growth! …

Raspberry Pi + iPad Pro

Teaching you how to install Kubernetes on your Raspberry Pi to demo out new ideas for learning purposes

Hello there friends! We’re back again with a fourth part in our series for enabling a Raspberry Pi to work directly with an iPad Pro. If you’ve been following along so far, you’ll recall that I wasn’t sure I’d write a fourth post. I’ve spent several weeks working on this specific post since, honestly, it’s been a struggle to get it working. Before we jump into why I’m writing this fourth post, I’d like to encourage new readers to get caught up by checking out the three previous posts:

I’m thinking about putting another bathroom in my basement.

I currently live in a nice but relatively modest house. Four bedrooms, two and a half bathrooms, and a mostly finished basement. Three of the bedrooms and both full bathrooms reside in the second floor of the house, and the fourth bedroom (which we use as a guest bedroom) is two levels below in the basement. As you can guess, this is less than convenient for guests who want to shower at their convenience and privacy. Fortunately, there is a rough-in for a full bathroom in the basement, which would totally…


Installing tools on your Raspberry Pi ranging from Docker to Git to JupyterHub

Welcome back, folks! We’re back again with our third and possibly final post in enabling a Raspberry Pi to work with an iPad Pro for data science work. If you’ve been following along so far, then you will already be able to connect the Raspberry Pi to your iPad Pro with a direct USB-C to USB-C connection. In case you missed those first two posts that have gotten us tho this point, here they are again:

In this post, we’re going to cover getting all our data…

Raspberry Pi + iPad

Walking you through the set up to have the iPad Pro and Raspberry Pi talk to each other via a hardline USB-C connection

Hello again, friends! We’re back again with the next post in our series in using a Raspberry Pi as a “computational DS accessory” for use with the iPad Pro. In case you missed the first post, please check it out via the link below as this post will build on top of that first one:

At the end of our first post, we had just gotten the Raspberry Pi’s OS initialized and working with a hardwired monitor/keyboard/mouse. You setup might currently look something like this:

Raspberry Pi + iPad

Getting you going for iPad + Pi work from unboxing to OS initialization!

A few weeks ago, I wrote a post about the state of being able to perform data science activities on an iPad Pro. While I was truly surprised to see how far Apple has come in recent years, we still aren’t 100% to the point that somebody can ditch their laptop to solely do things on an iPad. I personally would love this to happen just because I love using my iPad for literally everything else, from graphic design to using the screen for my piano sheet music.

As I quote from my last post:

Because iOS isn’t a traditional…


Using the MLflow server client to programmatically interact with your content in MLflow

Hello there all! Long time, no see, right? My previous post in this series was published all the way back in October 2020, which is coincidentally the time when a ton of new video games rolled out. Because I write these posts in my free time, I clearly was using my free time for other things. 😂

This will be the fourth and likely final post in our MLflow 101 series. It’s been a great ride, but all good things must come to an end. …

Office Hours

Helping you optimize your workflow by organizing your everyday practices

In my day job as a machine learning engineer (MLE), I juggle quite a few balls. I support several models in production, actively work on many new modeling efforts, participate as an admin for our area’s regular “skills team meeting”, and serve as my MLE team’s scrum master. I’m always the guy to say “yes” to any request and am more than glad to help a teammate stuck on something.

What might surprise you is that I would not consider myself a very busy person.

Don’t get me wrong, I keep busy all the time. (If my manager is reading…

David Hundley

Machine learning engineer at a Fortune 50 company, 5x AWS certified, 2x HashiCorp certified, 1x GCP certified, M.A. in Organizational Leadership, PMP, CSM

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store