This job offer is no longer available
About
About Us
This internship is hosted by
PAI (Precision Athletics Intelligence) , a new AI athletic program by
Putnam Science Academy (PSA)
- one of the most elite basketball-focused high schools in the U.S. PSA has won
5 National Prep School Basketball Championships , in 8 years, most recently in
March 2025 The school's mission is to deliver
world-class private high school education
while developing players for
NCAA and NBA levels PAI is built to bring
AI into high-performance sports and education , starting with this summer MVP project This is PAI's
first technical initiative , aiming to create a foundational performance analysis platform for PSA's nationally ranked basketball program - with high visibility and real-world application from day one. What You'll Build
You'll join a small, focused team building an end-to-end system to:
Automatically analyze practice footage Detect key actions (shooting, movement, defensive effort) Deliver structured feedback to coaches and players within minutes This product is aiming China Market and it will serve elite athletes and coaching staff immediately, with long-term potential to scale across teams and domains.
Your Role
As an ML intern, you'll work on the core computer vision pipelines that power the system. Responsibilities
Use or fine-tune models like
YOLOv8 ,
OpenPose , or
MediaPipe Build pipelines to extract training insights from video Process raw frames into structured data (e.g. player tracking, shot detection) Evaluate models on accuracy, reliability, and latency Deliver usable outputs via APIs to frontend/dev teams Write modular, reproducible code for experimentation and iteration What We're Looking For Core Skills
Strong Python skills; comfortable with Jupyter, scripting, and code structure Experience with PyTorch or TensorFlow - or fast learning capability Comfortable using OpenCV and working with image/video data Familiar with Git and collaborative development environments Fluent spoken Chinese (Mandarin) Mindset
We're looking for someone who: Has
real confidence
in their ability to learn fast and figure things out independently Can take
vague or high-level product goals , and turn them into working code Works through ambiguity with speed, structure, and clarity Cares about doing real work that gets used - not just academic experiments Is genuinely
interested in basketball
and understands the game at a basic level Thrives in a builder-style environment with ownership, speed, and open problems Bonus (Not Required)
Projects involving video analysis, pose estimation, or CV pipelines Experience with DeepSORT, sports heatmaps, or action recognition Familiarity with serving models via FastAPI, Flask, or REST endpoints Background as a player, coach, or data analyst in sports Who Can Apply
We welcome candidates from a variety of backgrounds:
Undergraduates
(junior/senior preferred) with strong project experience Master's students
in CS, AI, or related fields PhD students
focused on applied machine learning Self-taught engineers
- if you've built real things, we want to see them We value your ability to build and think clearly over your academic label.
Why This Matters
This is not a typical early-stage internship.
While our tech team is just starting out, our platform isn't. You'll be building within a system that already has:
A
championship-level basketball program Immediate real-world users : athletes and coaches with daily training needs A founder with full access to decision-making, facilities, and execution A high-trust environment where things move fast, and feedback is real In many ways, PSA provides what most startups seek after Y Combinator:
A live environment, institutional support, immediate demand, and the room to build and scale.
If you have:
Strong learning ability Clear technical thinking Ambition to turn
huge
ideas into real systems
...and you're excited by sports, education, AI, and building things from scratch - you'll thrive here.
Languages
- English
Notice for Users
This job was posted by one of our partners. You can view the original job source here.