• Led a team of 5 software engineers developing general autonomy software through 4 sprints; planned program increments and sprints, ran all meetings, onboarded multiple employees, reported to key stakeholders; resulted in completion of a major refactoring of our code base

• Spearheaded architecture of a Python-based data collection system for autonomy research; guided a team of 4 engineers through design implementation; oversaw software integration with 4 partnering projects

• Performed hardware installation, software integration, and software execution on 5 test flights, resulting in successful data collection on all flights

• Developed novel data filtering and aggregation algorithms for biometric data using statistical and signal processing techniques

• Wrote a real-time 3D data dashboard resulting in reliable system monitoring and 30+ FPS visualizations used for 10+ demos

Worked on development of computer vision algorithms and systems for construction robotics. Accomplishments include:

• Development of wooden stud detection system using LIDAR, Intel L515 cameras, Raspberry Pis, ROS2, and OpenCV. Currently enables the construction of wall panels as part of research and development.

• Development of a robot recording system using security cameras, CVLC, and Bash. Used to identify multiple issues with the robots during research and development.

Wrote requirements, designs, code, and tests for debugging applications for Logos using C++, OpenGL, Bash, and Make.

Accomplishments included:

• Design and development of an image viewing and recording system using C++ and OpenGL (4000+ lines of clean, well-documented code). Became critical in enabling success of field tests.

• Design and development of a command line search tool for other developers using Python.

• Assisted in debugging a Ruby on Rails project.

Assisted a graduate student in designing datasets, machine learning models, and synthetic dataset generation software. Presented research to 3 computer vision-based companies in the Orlando area. Edited and contributed content towards a research paper on deep learning-based image cropping and enhancement. Research was accepted to IEEE International Conference in Image Processing 2020.