About Hoop Dreams Basketball
Hoop Dreams Basketball is a skill development training business founded in 2002, helping boys and girls from elementary school through professional levels improve their game. We run training sessions every day except Friday, all based out of the Portland Athletic Club (5803 SW Beaverton Hillsdale Hwy., Portland, OR 97221). We also support athletes through evaluation, consulting, scouting, and college placement. Learn more at http://www.hoopdreamsbasketball.org.
Role Overview
We're hiring a full-time Machine Learning / AI Engineer to help us build the intelligent systems that power athlete development, performance analysis, scouting, and internal decision-making. You'll design and ship models and AI-driven tools — from predictive performance analytics to game-footage insights — that give our coaches, athletes, and leadership a real competitive edge. You'll work closely with our CEO, operate with a high level of ownership, and help lay the foundation for a future technical and data team.
Location
Remote
Start Date
Target hire date: as soon as possible.
Compensation
$110,000–$130,000 per year (based on experience and fit).
Responsibilities (What You'll Do)
- Design, train, and deploy machine learning models that support athlete evaluation, performance prediction, and player development recommendations.
- Build AI-driven tools — including computer-vision analysis of game and training footage and/or LLM-powered assistants for scouting, reporting, and communication.
- Develop and maintain data pipelines that turn training, athlete, and business data into clean, model-ready datasets.
- Own the full ML lifecycle: data preparation, feature engineering, model training, evaluation, deployment, monitoring, and retraining.
- Document models, systems, and workflows so future team members can ramp up quickly.
Must-Have Qualifications
- 3+ years of experience building and deploying machine learning models in production.
- Strong programming skills in Python and its ML/data ecosystem (NumPy, Pandas, scikit-learn).
- Hands-on experience with at least one deep learning framework (PyTorch or TensorFlow).
- Solid grounding in ML fundamentals: feature engineering, model selection, evaluation metrics, and avoiding overfitting/data leakage.
- Demonstrated experience with data analysis and pipelines (reporting, KPIs, aggregation, data cleaning).
- Comfortable working with SQL (schema design, queries, performance basics).
- Experience building and integrating REST APIs to serve models and connect external services.
- Ability to work independently with high ownership and minimal oversight.
- Strong communication skills—able to explain technical and modeling tradeoffs to non-technical stakeholders.
Nice-to-Have Qualifications
- Experience with computer vision (pose estimation, object/player tracking, video analysis) — especially applied to sports.
- Experience with LLMs / generative AI (prompt engineering, retrieval-augmented generation, fine-tuning, agent tooling).
- MLOps experience: model deployment, versioning, monitoring, and retraining pipelines (MLflow, Weights & Biases, or similar).
- Experience with analytics/BI tools (Metabase, Looker Studio, Power BI, Tableau, etc.).
- Experience with ETL / ELT tooling and data modeling practices.
Suggested Tech Stack / Tools (What We Expect You'll Use)
- ML / Modeling: Python, scikit-learn, PyTorch or TensorFlow, Pandas/NumPy; OpenCV or similar for vision work.
- AI Services: OpenAI / Anthropic / open-source LLM APIs for generative and assistant features as needed.
- Serving/Backend: Python (FastAPI/Flask) for model APIs; Node.js where useful for web tooling.
- Frontend: React or server-rendered templates for dashboards and internal tools.
- Database: PostgreSQL to start; growth path for larger data and feature stores.
- Hosting/Infra: Cloud hosting (Render/Fly/AWS/GCP) + object storage for datasets, models, and backups.
- Reporting: SQL + dashboards (Metabase/Looker Studio) + scheduled reports.
- Integrations: Stripe, email (SMTP/SendGrid), Google Calendar, SMS (Twilio) as needed.
- Quality/MLOps: GitHub, CI, experiment tracking (MLflow/W&B), automated backups, logging/monitoring.