Luke Harries

Hi! I'm an entrepreneur and software engineer,
working at the intersection of machine learning and medicine.

Scroll to find out more 👀


About Me

I'm on a mission to solve real problems at scale, particularly in healthcare.

To date, I've approached this in several ways: building companies; working as a contract software engineer developing websites, apps, and machine learning pipelines; and consulting for early-stage tech startups on product development, technical hiring, and outsourcing. 

I'm currently an AI Resident at Microsoft Research Cambridge. Previously, I studied the MSc in Computer Science at UCL, completing my thesis with Cambridge Cancer Genomics, a Y Combinator backed BioTech Startup. Before, I studied Medicine at Cambridge where I was the founding President of the Cambridge StartUp Society hosting events with startup founders and venture capitalists. My work on cognitive neuroscience was published. Alongside, I co-founded Proteam, which we grew to be the largest platform for intra-university sport in the UK.


Here are two of projects that I am particularly proud to have been involved with.

Deep Learning for Detecting Cancer Mutations 🔬

I completed my master's thesis with Cambridge Cancer Genomics (YC S17), leading the development of SomaticNet - a novel method for detecting cancer mutations.

The resulting paper was accepted at the Machine Learning for Health workshop at NeurIPS 2018 and the tool is publically available via CCG's website.

diagram explaining somatic net
diagram explainig somatic net

Proteam 🏉

During my final year at Cambridge I co-founded and was CTO of Proteam which we built to solve the lack of organisation of University Sport.

The iOS and Android apps allowed students to follow teams, get notified of upcoming games, create team-sheets and much more.

We grew the platform to 9,000+ users across 6 Universities.


From idea to prototype in 24-hours!

headshot of Luke looking happy


🎉 Winner of HackCambridge 2019

We developed a tool to gamify physiotherapy workouts by using machine learning to classify poses. The aim is to increase adherence of at home workouts. All training and prediction is done in-browser using Tensorflow.js, reducing any reliance on servers and meaning your images never leave the computer - maintaining privacy.

headshot of Luke looking happy


🎉 Winner of HackCambridge's Microsoft Prize 2018

For the millions of people with Visual Impairments, images online are inaccessible. We created a chrome extension which uses machine learning to automatically generate the missing image captions. The captions describe what's in the photo, who they are, and what any text says.

Visit for more information.

headshot of Luke looking happy


🎉 Winner of Allia's Serious Impact Hackathon 2017

We created the proof of concept for faster, cheaper and more accurate screening of Macular Degeneration. It is built for Google Cardboard which turns any phone into a VR headset.

Our solution has three parts:
1. Mapping the functional visual field
2. Increasing awareness of what it's like living with MD
3. Warping a real-time camera feed to move images out of your blind spot

Visit Github for more information.

I love meeting people working on exciting things. If we haven't already met, reach out and let's phone or grab coffee! ☕