Last updated 02/04/2022

I am a graduate researcher at Georgia Tech’s Aerospace Systems Design Lab and I will be defending my PhD thesis in early 2022. Keep reading below for a quick rundown.

📧 Getting in Touch  The best way to reach me is via email at me@raphaelgautier.com.

🎯 Objectives  I am currently seeking a full-time engineering research position. I am eager to join a team to leverage the skills I have developed and participate in tackling challenging engineering problems while contributing to my research domains of interest.

My interest lies in the development and implementation of computational methods that help solving real-life engineering problems. This includes supervised learning methods to create surrogate models of expensive simulations or physical experiments, Bayesian methods to quantify epistemic uncertainty and create more robust models in the presence of limited observations, as well as more general probabilistic models, uncertainty propagation, engineering optimization, designs of experiments, and adaptive sampling. I also have experience with modeling and multi-disciplinary analysis.

🔨 Skills  An essential part of my work as a research assistant was to produce clear and complete presentations of my work for sponsors and stakeholders. As a result, I pay a special attention to the quality of all my work products. Through my participation in multiple collaborative projects, I had the opportunity to work with teammates from different backgrounds and levels of expertise and to develop good teamwork skills.

On the technical side, the predictive models investigated in my thesis were implemented using numpyro and Google’s JAX, but I am also familiar with the main machine learning and Bayesian inference frameworks. I am comfortable developing software collaboratively using git, prototyping GUIs, and creating interactive data exploration dashboards. I have mostly been using Python recently, but I also have prior experience with Matlab, C, Java, and R. I am generally curious and always open to learn about new concepts, tools, and frameworks.

📒 PhD Thesis  My doctoral research focuses on the development of methods facilitating the creation of surrogate models for expensive-to-evaluate functions with an high-dimensional input space. There are three main parts to it. I first proposed a fully Bayesian approach to approximation by ridge functions and showed that it outperforms existing state-of-the-art methods in terms of predictive accuracy on a set of benchmark engineering datasets. Then, I extended this approach to the multi-fidelity context by modifying a deep multi-fidelity Gaussian process and showed that, under certain circumstances, it is beneficial to use both low- and high-fidelity evaluations. Finally, I explored ways to use the uncovered low-dimensional subspace to sample the expensive function and found that, if used to perform a design of experiments (DOE), it yields predictive models with higher predictive accuracy than if the DOE was done in the original high-dimensional input space.

🎓 Background  I did my undergrad in France, starting in 2010 with preparatory school where I acquired solid foundations in math and physics. After taking the nationwide engineering competitive exams, I joined Supélec, a top-tier engineering school where I studied computer science, electrical engineering, and controls. I started my Master’s in aerospace engineering at Georgia Tech in 2014, taking my core classes in aerospace design, fluid mechanics, and aerodynamics. After completing my Master’s in 2016, I carried on with a PhD.

I was employed and funded as a graduate research assistant throughout my graduate studies. My multidisciplinary background brought me a variety of skills that I have been using daily to find creative solutions to the problems I encounter in my projects. The PhD has allowed me to further develop my ability to efficiently plan and execute my work in an independent manner.

🧔 About Me  I like traveling, reading, and spending time with friends and family in my free time. I am a free software enthusiast and I enjoy tinkering to set up self-hosted services on my homelab or to try to make calls on a smartphone running GNU/Linux.