Background

Building a world where materials development is transformed by the power of AI. I am looking for new research opportunities to hone in my machine learning skills and apply them to real-world applications in materials development laboratories. Let's connect and build a better world together!

Job experience

• January 2021 - present
  Senior Data Engineer
  EveryDay Labs
  

  Redwood City, CA, USA

  - designed, built, and maintained scalable and efficient ETL data pipelines using AWS-based technologies to ingest, normalize, transform, and process client data.
  - developed a new QA suite to streamline the data quality check processes; reduced the need for manual data spot-checking, and decreased the production errors by over 50%
  - mentored entry-level and junior-level staff on various R&D projects; guided regular code-reviews and assisted in regular code-pair sessions.

• October 2020 - December 2021
  Materials Science Research Engineer
  Ford Motor Company
  

  Dearborn, MI, USA

  - performed an extensive literature review of current PA66-based composite materials in the automotive, transportation, and defense industries
  - developed new polymer-matrix composite formulations with highly conductive properties
  - created new methods for testing the electrical and thermal conductivity of insulative materials
  - deployed on-prem and cloud-based SQL warehouse servers to store data for several R&D teams
  - developed ETL pipelines to securely transfer data off laboratory testing equipment
  - created pre-processing scripts to clean ambiguous material datasets
  - developed AI/ML algorithms to assist with the prediction and development of new material formulations
  - created a web app to view, sort, export, import, and visualize data from the SQL warehouse server
  - performed A/B testing on the web app to optimize scripts and web app processes

• January 2019 - December 2019
  Undergraduate Research Fellow
  University of Michigan
  

  Ann Arbor, MI, USA

  - investigated the use of a Convolutional Neural Networks (CNN) for intergranular crack characterization in neutron-irradaited stainless steel 304 and 316.
  - gathered, processed, and labeled SEM image data for use in training, testing, and validation
  - developed a machine learning algorithm to perform crack identification and characterization in microstructural images of neutron-irradiated stainless steel
  - created the aforementioned algorithm in MatLab utilizing BioInformatic and Deep Learning toolboxes
  - performed validation on the algorithm with mean validation results ranging from 82-96% accuracy
  - optimized the crack characterization process by eliminating the need for manual testing and increasing the process productivity by over 10,000%
  - authored a peer-reviewed paper on the results of this algorithm and developed a tutorial for using this code in a lab-wide setting
  - presented the findings of this project at the Winter 2019 Michigan Design Expo at the University of Michigan in Ann Arbor, MI.

• May 2019 - August 2019
  Metallurgical Engineer Intern
  Rheinmetall Automotive
  

  Auburn Hills, MI, USA

  - performed failure analysis, run parts analysis, non-destructive testing, and microstructural and microchemical inspection on automotive pistons and bearings
  - practiced imaging techniques with SEM, optical microscopes, and stereoscopes, for microstructural inspection
  - performed non-destructive, dye-penetrant inspection on automotive pistons
  - developed and optimized a process to simplify the communication and documentation between customer inquiries and lab testing and analysis work
  - delivered technical test reports and inspection results for customers and company application engineers, project managers, design engineers, and company foundry engineers.

• May 2016 - August 2018
  Research Assistant
  Argonne National Laboratory
  

  Lemont, IL, USA

  - performed extensive literature review of academic journals, forecast reports, and online databases for information pertaining to the capacity, location, construction, and operation of all energy generating systems supporting the United States energy grid including petroleum, natural gas, renewable energy, and nuclear energy
  - developed energy storage models to demonstrate the need for emerging energy storage and battery technologies to support the United States energy grid in combination with a renewable-energy dominant energy market
  - developed energy market forecast models for emerging energy generation technologies relevant to supporting the energy grid
  - integrated the forecast model results into an agent-based energy generation network to aid in understanding the flow of energy throughout the energy grid
  - created the agent-based network utilizing SQL and Python
  - co-authored a peer-reviewed paper on the results of the literature search and preliminary results of the agent-based network model

Education

• University of Michigan
  B.S.E. in Materials Science and Engineering
  

  2017 - 2019
• Joliet Junior College
  A.S. in Science
  

  2015 - 2017