About

I am Meisam Hasani, an AI lead engineer based in Tokyo. I build computer vision systems that have to work in the real world: on moving vehicles, in warehouses, inside medical scanners, and on small embedded GPUs.

Most of my work sits where the model meets the hardware — choosing and calibrating cameras, getting geometry right across several views, and making the whole pipeline fast enough to run where it is needed. I studied biomedical and electrical engineering, and I enjoy carrying ideas between fields.

Selected experience

2026 –

Vision system architecture for logistics: multi-camera geometry, scene understanding, detection and tracking.

2023 – 2025

Automated digital pathology scanner: led the Python-to-C++ migration of the main system; real-time multi-level focus and image reconstruction with CUDA on NVIDIA Jetson; camera and encoding modules. Received the company’s Stellar Award (2024).

2021 – 2023

Robotics perception with ROS 2: LiDAR point-cloud calibration engine, 3D volume estimation, model compression.

2015 – 2021

Technical project manager for a licence-plate recognition and traffic control platform deployed on 300+ roads and highways; OCR at 98.7% accuracy across six countries’ plates; stereo and monocular speed detection at 98% accuracy. Earlier: medical image analysis for blood-cell microscopy.

Selected publication

Nitta N. et al. “Clinical-grade autonomous cytopathology through whole-slide edge tomography.”Nature 651, 472–481 (2026).nature.com

Education

• MSc, Electrical Engineering (Bioelectric) — University of Tehran
• BSc, Biomedical Engineering — University of Isfahan

Languages

Persian (native), English (fluent), Japanese (intermediate).

Get in touch

For questions about a vision problem, or to compare notes on something I have written: hello@tabanvision.com