Data Scientist

Cameron Lyons

Austin, TX

Tel: 703-***-**** *******.******@*****.*** GitHub: https://github.com/Cameron-Lyons/ Professional Experience

Coyote Logistics

Data Scientist

April 2022 – Present

• Develop a GNN with convolutional and edge regression modules written in PyTorch to predict cost to service contracts and reduced MAPE from 13.7 to 8.2

• Used MLFlow and Python to test different models, iterate on the models and promote the model that was performing the best and speed up iteration

• Created Airflow DAGs in Python to retrieve data from Snowlake data warehouses and SQL databases and produce features for the models speeding up training and inference and allowing for parallelization

• Develop a PySpark backtester using Python and SQL for efficient model testing and creating confidence intervals for models

• Use OCR to extract text from pdfs and images and then use LLMs to extract import metrics and classify documents related to facilites Environment: Python, NoSQL, SQL, PyTorch, Linux, MongoDB, Scikit-Learn, Apache Spark, Apache Airflow, Snowflake, Databricks, FastAPI, MLflow, Kubernetes, Bash, Git, Pandas, Terraform, NumPy, NetworkX, Agile Methodologies, Jupyter Notebooks Harver

Data Scientist

Dec 2020 – April 2022

• Fine tuned LLMs Using TensorFlow and Transformers in AWS SageMaker to recommend candidates based on answers to interview questions saving clients thousands of man hours

• Used PySpark and Python to analyze Dollar General turnover and make recommendations that reduced churn by 5.8%

• Trained and deployed model to recommend candidates for Enterprise leading to 12% increase in sales

Data Analyst

May 2019 - Dec 2020

• Built internal tools in Python for validations studies reducing time to complete by 60%

• Developed pipelines using Python to populate dashboards for clients

• Created tables in a SQL database in AWS to store important information for future analyses and built pipelines to populate tables

• Earned a promotion to Data Scientist in December of 2020 Environment: Python, NoSQL, MySQL, SQL, MongoDB, TensorFlow, Linux, Scikit-Learn, Apache Spark, AWS Databricks, AWS SageMaker, Natural Language Processing, spaCy, Mlflow, Kubernetes, Bash, Git, Pandas, NLTK, R, NumPy, Agile Methodologies, Texas A&M School of Public Health,

Undergraduate Research Assistant June 2016 – Nov 2016 College Station, Texas

• Created a database and forms that allowed for information to be added remotely

• Used R to clean and transform data for regression analysis Education

MS, Applied Data Science, University of Michigan, December 2021 BS, Economics with a Minor in Mathematics, University of Houston, May 2019

Contact this candidate