Matteo Macchini
About Me
Hello stranger! I am Matteo — engineer, AI researcher, and body language nerd. I build end-to-end machine learning systems for XR, from sensor data and model training to on-device deployment — making digital humans feel like real humans using AI.
My path started at CERN, designing motion control systems for particle beam diagnostics. I then spent six years at EPFL researching body-machine interfaces for robot teleoperation — work cited over 200 times and recognised with the Best PhD Thesis award in 2021. Now I lead avatar systems at Magic Leap, bringing real-time human presence into mixed reality.
Skills & Tools
Languages
Italian
Native
English
Fluent
French
Fluent
German
Basic
Let's be in touch!
Experience
Staff ML/AI Engineer — Digital Humans
Sep 2024 — PresentGoogle · MagicLeap partnership · Zurich, CH
- Led and shipped an open-source avatar project to showcase perception APIs.
- Spearheaded a fitness app featuring an embodied Gemini agent, demonstrating AI + XR + Body Tracking; shortlisted in internal 2025 audio-to-animation efforts.
- Leading two ongoing projects on full-body pose estimation from partial body tracking and inertial sensors.
Staff ML/AI Engineer — Digital Humans
Sep 2021 — PresentMagic Leap · Zurich, CH
- Led a 5-engineer team to ship the core ML2 Avatars system, enabling remote collaborative XR experiences.
- Managed end-to-end development of multiple AI/ML projects: hand pose classification, action recognition, and more.
- Productized key AI/ML solutions, promoting them to company-level systems for Magic Leap 2.
- Owned the Avatar system's software stack (Unity3D/C#) including data collection, networking, and animation.
Doctoral Researcher — ML for Human-Robot Interaction
Jul 2017 — Sep 2021EPFL · Lausanne, CH
- Developed beyond-state-of-the-art machine learning methods for body motion data processing.
- Published 7 first-author peer-reviewed papers in top-tier journals and international conferences.
- Teaching assistant across 6 master courses including aerial robotics and machine learning.
- Supervised 25+ semester, master, and internship projects; initiated 3 international collaborations.
Data Analyst & Lab Coordinator
Jul 2015 — Sep 2017CERN · Geneva, CH
- Led development of an automated data analysis software for superconducting wire diagnostics.
- Commissioned, tested, and installed 6 industrial furnaces with corresponding LabVIEW acquisition systems.
- Increased lab efficiency by introducing automated experiments and improved diagnostics pipelines.
Projects
CERN
ACC 2017
Beam Wire Scanner
CERN
IEEE Trans. Appl. Supercond. 2016
Superconducting Wire Analysis
EPFL — PhD Research
Fly Jacket
EPFL — PhD Research
IEEE RA-L 2019
Personalized Telerobotics via Fast Machine Learning
EPFL — PhD Research
IEEE ICRA 2020
Hand-worn Haptic Interface for Drone Teleoperation
EPFL — PhD Research
IEEE RA-L 2021
Personalized Human-Swarm Interaction
EPFL — PhD Research
IEEE VR 2021
Impact of VR and Viewpoints in Drone Teleoperation
EPFL — PhD Research
IEEE RA-L 2021
Arm-Wrist Haptic Sleeve for Drone Teleoperation
EPFL — PhD Research
IEEE RO-MAN 2022
Body Segment Fitness for Intuitive Body-Machine Interfaces
EPFL — PhD Research
IEEE Trans. SMC 2024
Data-Driven Personalization for Diverse Robot Types
Magic Leap
ML2 Avatars System
Magic Leap
Hand Gesture Recognition
Magic Leap
Workshap
Magic Leap
Egocentric Action Recognition
Android XR
Android XR Development
Selected Papers
- M. Macchini, F. Schiano, and D. Floreano, “Personalized Telerobotics by Fast Machine Learning of Body-Machine Interfaces.” IEEE RA-L
- M. Macchini, T. Havy, A. Weber, F. Schiano, and D. Floreano, “Hand-worn Haptic Interface for Drone Teleoperation.” ICRA 2020
- M. Macchini, L. De Matteïs, F. Schiano, and D. Floreano, “Personalized Human-Swarm Interaction through Hand Motion.” IEEE RA-L
- M. Macchini, M. Lortkipanidze, F. Schiano, and D. Floreano, “The Impact of Virtual Reality and Viewpoints in Body Motion Based Drone Teleoperation.” IEEE VR
- M. Macchini, M. Frogg, F. Schiano, and D. Floreano, “Does spontaneous motion lead to intuitive Body-Machine Interfaces? A fitness study of different body segments for wearable telerobotics.” RO-MAN
- J. Emery, A. Barjau, B. Dehning, J. Herranz Alvarez, P. Lapray, and M. Macchini, “Design and validation methodology of the control system for a particle beam size measurement instrument at the CERN laboratory.” ACC 2017
- B. Bordini, A. Ballarino, M. Macchini, et al., “The bundle-barrier PIT wire developed for the HiLumi LHC project.” IEEE TAS
Oral Presentations & Invited Talks
- Open Science in Practice — “Body Motion as data source for Telerobotics.”
- Humans in Motion 2018 — “Drone piloting through Body Motion.”
- ICRA 2020 — “Hand-worn Haptic Interface for Drone Teleoperation.”
- IEEE VR 2021 — “The Impact of Virtual Reality and Viewpoints in Body Motion Based Drone Teleoperation.”
- IEEE Neuro-EMBS 2021 — “Personalized Body-Machine Interfaces for Advanced Human-Robot Interaction.”