Taylor Smith
Director Of Engineering at Toyota Connected North America
Dallas, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolTaylor Smith is a Director of Engineering and seasoned machine learning architect with 12 years of experience building production-grade AI systems, currently leading engineering at Toyota Connected North America. He has guided teams of ~20 engineers to take state-of-the-art NLP from paper to production for cloud and edge virtual assistants, architecting event-driven training platforms and deploying TensorFlow models as both gRPC microservices and quantized edge graphs. A pragmatic engineer who emphasizes the “engineering” in MLE, Taylor spans data pipelines, model research, and client integration while owning P&L and product-aligned roadmaps. He’s an active open-source contributor and the author of pmdarima, Python’s auto-ARIMA equivalent, reflecting deep expertise in time-series modeling beyond typical NLP work. Based in Dallas, he pairs an MS in Business Analytics with hands-on systems experience in Python, Golang, Rust, and Kubernetes to deliver measurable business impact.
12 years of coding experience
11 years of employment as a software developer
Master of Science (M.S.) Business Analytics, Master of Science (M.S.) Business Analytics at Texas McCombs School of BusinessBachelor of Arts (B.A.) Psychology, Bachelor of Arts (B.A.) Psychology at Texas A&M University
Spanish, Arabic
Stackoverflow
7,010reputation
726kreached
150answers
37questions
machine-learning
top-5%
scikit-learn
top-5%
python
top-5%
pandas
top-5%
Github Skills (19)
python10
pandas10
time-series10
statistical-models10
data-analysis10
data-visualizations9
kmeans9
machine-learning9
data-visualisation9
scikit-learn9
data-visualization9
unit-testing7
pip6
tensorflow6
categorical-data6
Programming languages (11)
Github contributions (5)
alkaline-ml/pmdarima
Mar 2017 - Dec 2022
A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.
Role in this project:
Data Scientist
Data ScientistContributions:34 releases, 74 reviews, 1072 commits in 5 years 9 months
Contributions summary:Taylor's contributions primarily revolve around time series analysis within the pmdarima library, specifically focusing on enhancing its capabilities. The commits demonstrate involvement in improving the model's performance by incorporating seasonal features, as well as in-sample predictions and confidence intervals. Furthermore, the user contributed towards documenting and benchmarking the functionalities of the auto-arima model and related tests, as well as integrating the new features.
forecastingfillpythontime-series-analysisvoid
alkaline-ml/pmdarima-docker
Jul 2019 - Nov 2024
Base Docker images used with the pmdarima repo
Contributions:5 reviews, 17 PRs, 36 pushes in 5 years 4 months
pmdarimadockerdocker-imagespmdarima-docker
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.