Vincent Clemson

+1 570-269-0242

🖥 https://prncevince.xyz

vincent.clemson@gmail.com

github.com/prncevince

linkedin.com/in/vincentclemson

x.com/prncevincecares

Education

The Pennsylvania State University 2017 - B.S in Mathematics | Minor in Statistics

Career Background

👋 Hi I’m Vincent. Over the past two years, I have traveled around the world, exploring 24 new countries & 10 US states.
I blog about using open source tools to analyze & visualize data. Previously, I worked at Booz Allen where I conducted & led a study on NATO¹ object detectors using commercial satellite imagery on the Bighorn AI edge kit team. Prior, I worked at Peraton for five years on a GEOINT² performance modeling & analytics team, where I analyzed billions of records of transactional data on geospatial imagery stored by the NGA³ to help optimize the NSG⁴. Additionally, I conducted data driven analyses in the fields of remote sensing & astrodynamics to support the systems engineering & integration of the US national security satellite mission NTM⁵-L. Here, I promoted open source software development best practices and data science tooling usage in Python & R. I managed my team’s corporate & government GitHub accounts, growing the organization from 0 to 300+ repositories.

AI Engineer – Booz Allen Hamilton – CTO

Conducted a statistical performance analysis for evaluating Preligens’ aircraft & building geospatial computer vision algorithm detector models for Booz Allen’s Chief Technology Office 🛩 🏘️

i.e. Developed a Python module for querying web API against thousands of labelled Maxar satellite images, leveraged polars for data engineering & conducting ETL, used R’s {sf} & {terra} for spatial analysis & performance stats, & created a Quarto website for documenting entire analyses, from abstract to results.
Designed & prototyped multiple iterations of a human performance dashboard for JSOC⁶ using Oura Ring soldier biometric performance data (e.g. R {flexdashboard}, PowerBI, & Tableau)

Systems Engineer – Peraton

Data science & analytics on the NGA’s enterprise systems engineering contract (NEE/SEIN)
Analyzed the majority of imagery product transactions sent across the IC (e.g. NRO⁷/NGA’s ground CONOPS⁸)
Wrangled large amounts of historical categorical, numerical, spatial, & temporal GEOINT metadata using extremely efficient in/out of memory tools (e.g. data.table, Apache Arrow, & Parquet file data lakes)
Designed ETLs to pull and join data from disparate sources (e.g. APIs, S3 buckets, and databases) into tidy datasets for analysis (e.g. tracked imagery transaction timelines from satellite tasking to processing / exploitation)
Designed, developed, & maintained dashboards, visualizations (plots & charts), & data lakes for reporting engineering performance statistics on satellite camera sensors, as well as military base / intelligence site comms
Conducted orbital mechanics analyses using ephemeris & simulators of an ABI⁹ satellite / ground sensor system
Prototyped, developed, & maintained modeling tools to conduct EDA on data for analyzing patterns, trends, & spatial/geometric relationships (e.g. ggplot2, sf, Plotly, Matplotlib, Leaflet, Dash, Shiny, Docker, & Cloud Foundry)
Statistical analysis on the performance, sizing, & budgeting of NSG imagery & their driving relationships
(e.g. linear trend models, bandwidth models, human-in-the-loop supervised/unsupervised EDA ML workflows)
Worked on a distributed team & operated in a cloud computing environment. Experience with building a cloud from the ground up, config management, & permissions (e.g. AWS, RStudio Server Pro, Unix/Linux, VPC)
Gathered analytics requirements from lead/chief engineers, as well as mentored team from juniors, peers, to leads on analytic capabilities in 1-on-1, open forum, & presentation environments.

Application Developer Intern – JP Morgan Chase

Agile development team in JP’s Technology Analyst Program. Team of six interns built a full stack Java-Spring tool aggregating data for the planning & execution of the migration & decommissioning of legacy JPMC data center servers. Worked frontend & backend. Led role as Scrum Master.

Data Analytics Intern – IMG Learfield & Penn State Athletics

Analyzed unstructured season ticket holder survey text data using NLP¹⁰ techniques & the NLTK in Python (e.g. tokenizers, collocations)
Performed Decision Tree Modelling in R for finding trends between customers and ticket sale renewals

What I’m interested in doing

Applying my skills in analytics, engineering, data science, & storytelling to help lead a team of individuals who are passionate about successfully accomplishing their mission. I enjoy contributing as a positively impacting team member.

Projects on the Web

Combining math & code into bite sized technical explanatory articles on my travel themed Project Euler listing
Designed aesthetic & interactive web maps in R using ggplot2, JavaScript, & SVG
Rapidly visualized natural disasters around the 🌍 by developing web map tools that dynamically tile satellite imagery from Maxar’s Open Data Program using STAC¹¹ & Leafmap
Developed & Deployed analytic Dash & {shiny} web apps in Python & R for NGA mission analysts to predict years of geospatial coverage of NTM Earth Observation Satellite Systems
Built Spatial Machine Learning Models using {mlr3} in R to run within GitHub Actions
Worked through all of Tomas Beuzen’s Deep Learning with PyTorch & ported it to render w/ nbdev & Quarto
Improved dev & data science workflows by teaching engineers to version control their code using Git
Created Quarto, R & RStudio CLI utility shims to handle multiple Quarto/R installations
Started developing an R package, {leaflet.super}, to visualize big geospatial data with Leaflet & Arrow
Built exploratory unsupervised clustering tools to drive insight from imagery analyst user activity data
Military wartime border region behavior is of interest within the geospatial intelligence domain, so I built tools for analyzing satellite image distance to border regions & for creating new geometric border regions
Quantifying size & types of collections (e.g different camera sensor modes) is critical in Earth observation satellite systems engineering, so I’ve built different analytical product mapping tools to help do so:
e.g. advanced Plotly map animations & interactive Leaflet htmlwidget heatmaps
I version control my MacOS dot-profile & config files for rapid dev/data-sci setup

Programming Skills

I have hands on expertise in using various Machine Learning, Data Analysis, Geospatial & Visualization Packages, Web Technologies (app frameworks & scraping tools), SSGs¹², & Notebook / Computational Medium tools.
Below is a non-exhaustive high level list of the technologies that I’m working in.
Python, Conda/Mamba, Jupyter, numpy, pandas, Docker, Kubernetes, SQL, JavaScript, Node.js, Bash, Zsh, tmux, VSCode, R, Quarto, R Markdown, GNU Make, GitHub Actions, Leafmap, Google Earth Engine, QGIS, GDAL

Machine Learning Skills

Some topics I’ve dived into while integrating machine learning workflows onto NSG transactional log data.
Spatial Cross-Validation Techniques, Discrete Event Simulation, Generalized Linear Models, Ensemble Models, Unsupervised Learning, Principal Components Analysis, Clustering Techniques, Feature Selection Other topics I’ve dived into through various ML workings. e.g. rebuilding Deep Learning with PyTorch.
CNNs (Convolutional Neural Networks), GANs (Generative Adversarial Networks), Gradient Descent, Regularization, Decision Boundary, One-vs-All Multiclass Classification, Backpropagation and Advanced Optimization techniques

NATO - North Atlantic Treaty Organization ↩︎
GEOINT - Geospatial Intelligence ↩︎
NGA - National Geospatial-Intelligence Agency ↩︎
NSG - National System for Geospatial-Intelligence ↩︎
NTM - National Technical Means ↩︎
JSOC - Joint Special Operations Command ↩︎
NRO - National Reconnaissance Office ↩︎
CONOPS - Concept of Operations ↩︎
ABI - Activity Based Intelligence ↩︎
NLP - Natural Language Processing↩︎
STAC - SpatioTemporal Asset Catalog ↩︎
SSG - Static Site Generator ↩︎