Résumé
Ten years building software and solving difficult technical problems. Motivated by curiosity, quick to learn new domains, and committed to honest, thoughtful communication.
Selected work, explained at length → selected work
Experience
I turn complex AI initiatives into reliable production systems. I research and evaluate approaches, refine product specifications around technical and business constraints, write implementation proposals, design architectures, and strengthen designs through peer reviews.
My work spans the full AI lifecycle, from early discovery through delivery and evaluation.
I developed dynamic, configurable cloud pipelines for data ingestion and ML operations on large data sources. I built a company-wide data layer to facilitate sharing large data sources among multiple products.
I built maps for autonomous vehicles on high-performance computing platforms. I contributed to architecture decisions that scaled the map-building process by orders of magnitude.
I worked directly with customers to understand their systems, often onsite — their constraints were the job, not an obstacle. I built and maintained core application device drivers and proprietary libraries in C++ and JavaScript to run on Linux. I integrated Kafka, Node.js, and other open-source technologies into a proprietary platform, then automated tests with MochaJS. I performed Linux system administration duties daily.
I held office hours to assist undergraduate students across a breadth of computer science topics. I graded assignments and exams, and helped maintain the course website.
Education
Georgia Institute of Technology
2021
Georgia State University
2016
Projects
A Kaggle challenge to identify, from a photograph of cassava leaves, which of four diseases is afflicting the plant or whether it is healthy. Training data was over 21,000 images crowd-sourced from farmers — heavily imbalanced and extremely noisy. Using PyTorch, I performed image augmentation and used a 50-layer residual network to reach over 70% accuracy on the test set, an 8.5% improvement over predicting the most frequent label.
A team effort on a UNICEF challenge to predict Human Development Index from country-specific data. I contributed ETL in Python and pandas over several large CSV files, aggregating related data and generating new data points by mapping independent but correlated sources — a 30x speed-up over naive iteration. I also contributed the loading and scaling of that data in D3 and Django.
A group project in MATLAB implementing an agent to play Go. For the game itself I contributed the recursive logic that efficiently determines when pieces are captured. For the agent I built a neural network from scratch, along with a genetic algorithm.
I connected an Arduino Uno, a motorshield, and a sonar to a Snap Circuits rover, then programmed it to drive autonomously while avoiding objects.