I'm a creative programmer, aspiring artist, and unapologetic media consumer obsessed with creating works that explore the world in new ways. In particular, I specialize in working with digital media through a multimodal approach based upon my technical background in machine learning and data processing. Currently, I am a backend engineer at Graphiant where I design the data systems underlying our edge computing centers. In my spare time, I am working on releasing a roguelite game and a instrumental rap album by the end of the year.
Transforming complex systems into compelling visual narratives. Through a comprehensive background in data storage, analysis, and visualization, I distill intricate information into accessible and impactful forms, enhancing the storytelling potential of projects.
Coding captivating auditory experiences. Whether it's autonomous audio synthesis or real-time audio-visual systems, I leverage my background in music production and audio language processing to design tools that allow users to engage with audio in new ways
Leveraging advanced algorithms to understand and create. From computer vision to natural language processing, I channel my varied expertise in machine learning to develop intelligent solutions that probe systems in creative new directions.
Programming unique artistic installments. Having projects ranging from game design to audiovisual experimentation to generative fractal design, I create works on the relationship between art and self by designing my code with flavor and personal meaning.
Explored the audiovisual storytelling of the show "Off the Air" using a variety of multimodal processing and machine learning tools. These include PCA clustering, K-means color extractions, frame-level audio classification, and real-time visualization of audio features.
Trained a machine learning model to extract posteriograms and word alignments from a song and then tested whether these features could be used to create more nuanced vocal source separation models. Described in research paper with code on Github.
Created a high-performance script that facilitates async calls within a multiprocessing framework to simulate an active music listener, allowing Spotify's API rate-limiting to be bypassed. This resulted in being able to extract almost all artists on Spotify (over 13 million) in a very small amount of time.
Designed an abstract mandala generator that constantly changes form using the current second, minute, hour, and day