# Vincent Quenneville-Bélair, PhD

> Applied Mathematician & Machine Learning Scientist — Vincent Quenneville-Bélair, PhD — Applied Mathematician and Machine Learning Scientist. Supply Chain Forecasting at Amazon, creator of PyTorch torchaudio.

## Contact & Links
- Website: https://vincentqb.github.io/
- Email: vincentqb@gmail.com
- LinkedIn: https://linkedin.com/in/vincentqb
- GitHub: https://github.com/vincentqb
- Google Scholar: https://scholar.google.com/citations?user=B3XqkfMAAAAJ

## Professional Experience
### Machine Learning Scientist — Supply Chain Forecasting, Amazon (2021 – Present)
- Design deep learning attention-based models to forecast product demand for supply chain optimization.
- Develop foundation forecasting model, unifying across products worldwide at multiple scales, deploying zero-shot for external partners.

### Machine Learning Engineer — PyTorch, Facebook AI (2019 – 2021)
- Create torchaudio library, engaging over 200 open source contributors.
- Develop speech-to-text and text-to-speech deep learning models.
- Integrate novel PyTorch optimizers collaborating with academic and industrial researchers.

### Machine Learning Scientist — Supply Chain Forecasting and Marketing Measurement, Amazon (2017 – 2019)
- Generate long-term strategic inventory capacity forecast. Model counterfactual scenarios. Optimize supply chain expansion recommendations.
- Build causal impact models to estimate advertising campaign lift. Infer future returns and optimize advertising portfolio.
- Teach internal machine learning specialization course series on matrix factorization, dimensionality reduction, and recommender systems.

### Chief Data Scientist — Vizanda (2016 – 2017)
- Develop web-based software to automatically extract information from structured and unstructured data on the fly. Process the information to programmatically generate relevant visualizations and intelligent insights.

### Chu Assistant Professor of Applied Mathematics — Columbia University (2015 – 2017)
- Model gravitational wave propagation to understand black hole collisions. Create and analyze novel specialized mixed finite element methods to simulate these models numerically.

## Education
- **PhD Applied Mathematics**, University of Minnesota
  - Honors & Awards: NSERC Alexander Graham Bell Canada Graduate Scholarship, FQRNT Research Scholarship, University of Minnesota Doctoral Dissertation Fellowship.
- **MCS Computer Science**, University of Minnesota
- **MSc Applied Mathematics**, University of Minnesota
- **BSc Mathematics and Physics**, McGill University