غازي شريف
Robotics engineer from ETH Zürich. AI and automation for life sciences at KVALITO. Co-founder of HyperBody.
Tap the ground to throw a ball
INU-01 is an animated robot dog. Throw it a ball, make it run to music, or watch it do graded push-ups.
EPFL for the bachelor, a year at Sorbonne in Paris, then the MSc at ETH Zürich in Robotics, Systems & Control. The coursework that stuck: deep learning for autonomous driving (3D point clouds, segmentation, depth), model predictive control, robot dynamics.
Master thesis: an RGB-D method to guide pedicle screw placement in robotic spine surgery. ZED stereo cameras, optical tracking, vertebra segmentation, and live tracking in ROS2 for the EU Horizon FAROS project.
Master focus project: I added hand movement data to gaze-based action recognition. Task recognition accuracy rose to 91%. Graded 5.5 out of 6.
The gym, measured. I built a form analysis engine: it tracks 33 body landmarks, splits a set into reps, scores depth, tempo and symmetry, flags faults by severity, and keeps a ghost of your best rep to compare against. 14 lifts, from back squat to lateral raise.
The same idea runs the form checks in HyperBody, the AI physique app I co-founded. Press Reps up top: INU-01 gets graded the same way.
Idea to shop floor with full P&L: budget, permits, suppliers, equipment, staff and SOPs. Up to 200+ units a day for 7 B2B clients and walk-in customers, at about 65% gross margin. The best operations course I have taken, and I paid for it myself.
Intellyse taught me the full SaaS sales cycle and how to automate a pipeline that books its own meetings. At KVALITO I build AI for GxP work: validation documents the AI drafts and a qualified person signs, compliance gates inside the ERP, and engines that turn public signals into account and supplier intelligence.
One rule everywhere: the AI drafts, a human decides.
Measured an observed result Designed how it is built, not a promise