Senior Computer Vision Engineer
Pubblicato il 12-08-2026 - Scandit in Milano
Scandit gives people superpowers. Whether enabling delivery drivers to make quicker deliveries, matching a patient with their medication, or allowing retailers to make store operations more efficient, our technology automates workflows. It provides actionable insights to help businesses in a variety of industries. Join us as we continue to expand, grow, innovate, and help take Scandit to the next level.
Si candidi qui sotto dopo aver letto tutti i dettagli e le informazioni di supporto relative a questa possibilità di lavoro.
We are now building a new generation of technology for retail: a computer vision–driven system that helps retailers to increase their profit margins through better operational insight and automation. As a Senior Computer Vision Engineer, you will play a leading role in taking this product from 0 to 1, owning key technical decisions and delivering production-grade vision capabilities end to end.
You will own the technical direction for action recognition in real‑world retail environments: from defining how we collect and annotate video data,
to prototyping and evaluating models, to iterating on precision, recall and end-to-end alert latency under production‑like conditions. You'll work closely with product, data, and engineering stakeholders to validate the riskiest assumptions quickly and cost‑effectively.
If you enjoy turning ambiguous, high‑impact problems into working ML products – and have experience building commercial computer vision systems for action recognition, autonomous checkout, worker safety, or similar applications – we'd love to talk.
About the role
As a Senior Computer Vision Engineer, you will be responsible for leading the technical discovery and early development of Scandit's new solution – from validating the riskiest assumptions to building and iterating on the first end-to-end prototypes. You will work closely with product, other engineering teams, and external stakeholders to turn real-world video data into robust, priv