Ellington Kirby

Logo

Software Engineer and Machine Learning Student

ellingtonkirby31 at gmail.com

Github

Twitter

Google Scholar

Download CV

I am a former Software Engineer and current Machine Learning Engineer. I have worked at large and medium sized companies as an Android Developer such as FanDuel and Snap Inc, as well as small startups and agencies. I am passionate about Deep Learning and Artificial Intelligence, and love to work at the intersection of research and engineering.

In 2019 I moved to Paris to learn French, work at Zenly, and eat way too many French pastries.

In 2022 I returned to school to pursue the IASD Masters in Machine Learning at PSL Research University.

Currently I am working at Valeo.AI as a research intern working on generative methods for 3D point cloud data in the context of autonomous driving.


Blog


Projects

Graph Clustering to Identify Road Networks with Similar Traffic Behaviors

As part of the GRETTIA Lab at Université Gustave Eiffel I worked to adapt the Leiden Algorithm to cluster road networks. The goal was to identify the temporal evolution of congestion conditions via clustering similar streets.

Here is an image of the Barcelona road network clustered by my aglorithm. The colored clusters represent groups of roads identified to have similar levels of congestion and average speed. Barcelona Clustering

I applied this method over a full day of data to evaluate how these clusters change with traffic demand. My method can be viewed on my github here

Fine Tuning BERT Models for Bio Medical Tasks

Second author on “Intégration de connaissances structurées par synthèse de texte spécialisé” (Integration of structured knowledge through specialized text synthesis)link, where we compared fine tuned BERT models against models trained using a curated dataset of specialized text.

Audio Localization Using Time Difference of Arrival

My first exposure to research was as the first author on smartphone based audio localization using time difference of arrival where I implemented a demo of Snooping Keystrokes with mm-level Audio Ranging on a Single Phone.


Work Experience

Zenly - Snap Inc

At Zenly I worked on the Conversations team alongside some of the smartest and most hard working people I have met in my life. We built so many creative features our users loved, like the Zenly Voice Notes, dozens of fun chat easter eggs, resizable (giant) text, the camera and Media Request feature (like the inverse of Snapchat). These features were used millons of time everyday and beloved by users. Unfortunately in 2022 Zenly was permanently shut down by Snap.

One of my favorite projects was my attempt to build an animated lip sync generation system for the voice notes feature. We had cute emoji faces that animated when the voice notes played, and I felt it would be perfect if they mouthed the users message. I read through a lot of the literature on lip sync generation, and tested several deep learning methods like Allosaurus. I attempted to build a Formant extraction system using Linear Predictive Coding which would map formants to mouth shapes. Ultimately we were recognized by the French Government’s CIR (Research Tax Credit Program) and accepted for a grant in experimental development. It was this experience that led me to consider returning to school and pursuing machine learning.

DRAFT - FanDuel

I was the solo Android developer on the original DRAFT Fantasy sports app for over two years. We built too many cool features to list and had a great time watching a ton of sports with an awesome team. After our merge into the FanDuel application, I moved to France while the former DRAFT team started a new project, where they are finding a ton of well deserved success, Underdog Fantasy. Instead of building a massively popular sports gaming application, I decided to try enable my croissant addiction. You tell me if I made the right choice!