Stefano Pini

Machine Learning Engineer at Wayve

Stony Stratford, England, United Kingdom
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
Stefano Pini is a Machine Learning Engineer with nine years' experience specializing in prediction and planning for autonomous driving, currently at Wayve after roles at Woven Planet UK (formerly Lyft Level 5). He holds a PhD in Computer Engineering and Science, with a research background in computer vision and deep learning for human-vehicle interaction. Stefano blends research rigor with production-focused engineering, having improved closed-loop planning evaluation, metrics, and visualizations in the widely used L5Kit repository and integrated multimodal models like SafePathNet into practical examples. Based in Stony Stratford, he brings a strong track record of turning academic advances into reproducible tooling and clear documentation that help bridge simulation and real-world driving stacks.
code9 years of coding experience
github-logo-circle

Github Skills (11)

pytorch10
machine-learning10
jupyter-notebook10
planning10
python10
vectorization9
evaluation9
eval9
faster-rcnn8
mask-rcnn8
documentation8

Programming languages (9)

C++CJavaScriptPHPHTMLRubyPuppetPython

Github contributions (5)

github-logo-circle
woven-planet/l5kit

Apr 2021 - Jan 2023

L5Kit - https://woven.toyota
Role in this project:
userML Engineer
Contributions:11 reviews, 12 commits, 20 PRs in 1 year 9 months
Contributions summary:Stefano focused on updating and enhancing the closed-loop evaluation process within the L5Kit repository, specifically within the context of planning tasks. The user modified and extended the `examples/planning/closed_loop_test.ipynb` notebook to incorporate new metrics for closed-loop evaluation, including code for metrics to assess performance such as displacement error and collision detection. They also made improvements to documentation and visualizations within the notebook. The user also integrated SafePathNet, a multimodal prediction model, and incorporated it into the documentation and examples, demonstrating experience with model implementation.
planningautonomous-vehiclesmachine-learningself-driving
stefanopini/hosts

Dec 2017 - Jan 2023

Contributions:8 pushes in 5 years 1 month
curated-sourcesmvpshostscategoryadditional
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Stefano Pini - Machine Learning Engineer at Wayve