About us
At TraceVision, we turn video (pixel data) into data computers can use. We want to teach computers to see the way humans can - with persistent memory, tracking, and emotional response to a scene or action. We've been pioneering real-world AI for over a decade, and we're cash flow positive - which means we're in control of our own destiny and growing!
Our flagship product, Traceup.com, delivers video highlights for parents of youth sports athletes. We're processing 8 billion frames of video daily and creating highlights for nearly 200,000 athletes each week. We've also expanded into security and retail sectors, with public companies building on Core Data across operations, merchandising, asset protection, and internal engineering teams.
We’ve been in love with AI before it became a buzzword and deployed our first models in production in 2015. AI writes a lot of our code, and we've developed internal frameworks that support our GTM teams (Sales, Customer Success, Support, Operations, Shipping) and engineering teams (code writing, processing supervision, annotations for model training). If you don’t believe that AI can be an effective salesman or can write production code, you won’t fit in!
We're a small team that works hard and takes ownership. Every employee here is a single point of failure. This is a high-stress environment and we often work on the weekends. We keep the main thing, the main thing. We're fully remote but meet once a quarter somewhere in the U.S. for onsite collaboration and intense brainstorming.
About the math team
Our Math Team develops novel models and algorithms for analyzing video data, scales them, and deploys them to our production data pipelines. We’re the team that takes pixels in and produces core data, the building blocks for applications consumers and enterprises love to use. We prefer to iterate, starting with an 80% solution that delivers usable data quickly, before refining and improving our results over time.
What you’ll be doing
Apply machine learning, computer vision, and signal processing techniques to real-world video data. Develop novel models and algorithms for analyzing video data. Research and explore existing solutions, learning new topics in detail when needed. Collaborate with the math team to refine ideas, models, algorithms, and analyses. Own projects all the way from definition, annotation, and proof of concept through to deployment. Work with the wider engineering team to implement production code, including providing written descriptions, specifications, and test data as needed. Participate in code reviews and contribute to our git repositories.
Technologies we use
Mostly: Python, TensorFlow, PyTorch, OpenCV
Some: bash, C++
Infrastructure: AWS (EC2, S3, Batch), GCP
Tools: MySQL, ffmpeg, git
What we’re looking for
Ability to tackle data analysis, machine learning, or model training projects. Experience analyzing, manipulating, and visualizing data. Ability to master new ideas from a wide range of fields, including math, engineering, physics, statistics, computer science and AI/CV/ML. Strong written and spoken communication on technical topics.
Python experience. Experience with one ML framework (TensorFlow or PyTorch). Familiarity with git. Bonus points for familiarity with OpenCV, shell scripting, C++, cloud infrastructure, MySQL, ffmpeg.
Self-directed and comfortable in a fast-paced environment. Willingness to take ownership, manage your projects, and work weekends at crunch time.
Things we don’t care about
Whether you finished a PhD. If you have a degree in AI, machine learning, computer vision, or even computer science.