About the role
Senior Computer Vision Engineer at Scandit (Scandit Italy), building a new generation of computer-vision technology for retail that automates workflows and gives businesses operational insight.
This role takes a new action-recognition product from 0 to 1: you would own the technical direction for recognising human actions in real-world retail environments, defining how video data is collected and annotated, prototyping and evaluating models, and iterating on precision, recall and end-to-end alert latency under production-like conditions. You would design end-to-end CV/ML pipelines on real video data, set up annotation workflows, and adapt state-of-the-art vision architectures for behaviour and action detection in unconstrained settings. It suits a pragmatic, experimental engineer who has shipped commercial computer-vision products (action recognition, autonomous checkout, worker safety or similar), with Python and modern ML/CV frameworks as core.
Highlights
- 0 to 1 ownership of a real-world action-recognition video-AI product
- End-to-end CV/ML pipelines, annotation workflows and state-of-the-art vision architectures
- Python and modern ML/CV frameworks core
- Hybrid, based in Italy, at a Great-Place-to-Work-certified scale-up
This recap is dataskew's editorial summary, not the company's copy.