Data Scientist

About me

I’m a Data Scientist at Rivian working on different projects and aiming to improve the quality of our product. To do so, I use Machine Learning (ML), big data, and big data tools, in particular, Python, Apache Spark, and Databricks, to leverage the data and develop prediction, diagnostics, and prognostic models. There are a lot of interesting project we are trying to solve. For example You might be surprised by the amount of work it takes to accurately estimate the State of Charge of your vehicle battery 🔋, or how the settings of your vehicle may change your tire degradation.

Previously, I was a postdoctoral researcher at Vanderbilt University, Department of Electrical Engineering and Computer Science. As a member of SCOPE Lab (Smart and resilient Computing for Physical Environment) under the supervision of Dr. Abhishek Dubey, I worked on multiple projects including developing Artificial Intelligence agents for integrated data-driven technologies for smart cities and analyzing transportation systems using network science. You can learn more about one our collaborative research projects with the Department of Transportation here. I earned my PhD from the University of Arizona under the supervision of Prof. Achintya Haldar focused on developing an intelligent integrated method for reliability estimation. Modeling the environment using statistical methods was another part of my research. During my internship, I collaborated as a Data Scientist on an NEH-funded project to develop a new OCR technique using Computer Vision (CV) and Long Short-Term Memory (LSTM) networks, and a hurricane predictive model using high-dimensional spatio-temporal data. Upon completion of my PhD, I also received The Outstanding Graduate Student Award in 2019. Additionally, I developed a model using Recursive Neural Networks (RNN) to imitate the response of a structure and find the location as well as the severity of the damage for my Master’s degree.

A comical adage by renowned economist Ronald Coase says:
“If you torture the data long enough, it will confess to anything”.
Even though this statement is ambiguous, I would prefer to be optimistic and interpret this as using the correct tools to coerce the data to a correct confession. The role of a data scientist is to find and apply the correct tool. I am passionate about working with numbers. Developing models to predict/imitate a behavior/feature is quite magical. I’m very interested in solving real-world problems by using machine learning and my data science knowledge. For fun, I follow Formula 1. It is, indeed, one of the most heavily-invested-in-data-science sports. During a race, thanks to the over 300 sensors on each car, more than 1.5GB of real-time data is transferred back to the engineers, ref.