Timothy D. Hopper


Cylance Inc, Raleigh, NC

Senior Data Scientist (November 2017 – )
  • Research and develop machine learning techniques for dynamic detection of malware
  • Train data scientist on software engineering practices with Python
  • Develop and maintained Python packages for data ingestion, cleaning, and standardization
  • Lead team in integrating best practices for Python development and software testing

Distil Networks, Raleigh, NC

Data Scientist (October 2015 – November 2017)
  • Researched and developed machine learning techniques for detection of malicious web bots
  • Lead research for validation of JavaScript-based client fingerprinting technique
  • Constructed hierarchical Bayesian models for analysis of internet user behavior
  • Primary developer of real-time identification platform for malicious web bots on Apache Storm
  • Developed Python-based internal tools for fast querying of data warehouse
  • Introduced team to best practices in Python development and data analysis

Qadium, Raleigh, NC

Data Scientist (February 2015 – October 2015)
  • Built open-source tools in C++ and Python for topic modeling and inference on nonparametric Bayesian models
  • Wrote instructional material for inference on nonparametric Bayesian models in with IPython notebooks
  • Maintain continuous integration with Travis-CI and automated deployment to Anaconda.org

Parse.ly, Raleigh, NC

Software Engineer (January 2014 – February 2015)
  • Developed algorithms in Python for aggregation of large-scale, streaming, time-series data
  • Built and maintained lambda architecture on AWS using Storm, Elasticsearch, Redis, and Cassandra
  • Contributed to streamparse, an open-source library for real-time stream processing in Python

RTI International, Durham, NC

Data Scientist (October 2012 – January 2014)
  • Provided analytics and computational support for one of the nation’s leading nonprofit research institutions
  • Projects included social media analysis for public health, development of environmental GIS modeling software, nonlinear mixed effect modeling, and text-mining-based crime forecasting software


North Carolina State University, Raleigh, NC

Master of Operations Research (August 2010 – December 2012)
  • Research area: Reinforcement learning methods for healthcare operations
  • Key Courses: Graph Data Mining, Machine Learning, Bayesian Networks, Linear Programming
  • Instructor: Calculus 2

University of Virginia, Charlottesville, VA

Graduate Student in Mathematics (June 2009 – May 2010)
  • Key Courses: Introduction to Mathematical Statistics, Complex Analysis, Real Analysis, Advanced Linear Algebra
  • Instructor: Calculus 1 and Calculus 2

Grove City College, Grove City, PA

Bachelors of Science in Mathematics (August 2004 – May 2008)
  • Minor in Applied Physics; Minor in Computer Science
  • Awards: Graduated Summa Cum Laude, Dean’s List with High Distinction, Presidential Scholarship

Open Source Contributions

Tool Experience and Skills

  • Programming Languages (high proficiency): Python
  • Programming Languages (intermediate proficiency): C++, C#, Mathematica, R, SQL
  • Programming Languages (some proficiency): Java, Javascript, Matlab, C
  • Data Processing Tools: Apache Storm/streamparse, (Py)spark, Pandas, Scikit-learn, Impala, Hive, Dask
  • Data Stores: Elasticsearch, Cassandra, MongoDB, Redis, MySQL