Senior Computer Vision Engineer (Action Recognition)

About Scandit

Scandit is expanding its technology to build a new generation of computer vision–driven systems for retail, aiming to increase profit margins through better operational insight and automation.

About the Role

As a Senior Computer Vision Engineer, you will play a leading role in taking a new 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 data collection and annotation to prototyping, evaluating models, and iterating on performance under production-like conditions. This role connects cutting-edge CV/ML research with real-world product constraints, requiring deep technical expertise and a pragmatic, experimental approach.

What you will do

• Define and prioritize technical experiments to validate key risks for computer vision models in retail stores.
• Design and implement end-to-end CV/ML pipelines on real-world video data, from data ingestion and preprocessing through model training, evaluation, and deployment.
• Set up and refine human annotation workflows to create high-quality training and test datasets from video streams.
• Collaborate with product managers and engineering leaders to clarify requirements and translate business needs into technical roadmaps.
• Select, adapt, and optimize state-of-the-art computer vision architectures for suspicious behavior and action detection.
• Provide technical leadership in video-based computer vision applications, shaping best practices and future hiring.

Who you are

• University degree in Computer Science, Electrical Engineering, Mathematics, or a related technical field.
• Significant hands-on experience in computer vision and machine learning, including designing, training, evaluating, and deploying models in production.
• Proven track record of building end-to-end CV/ML systems from 0→1 (ideally commercial products).
• Strong expertise with video-based pipelines and human action or behavior recognition (e.g., retail, autonomous checkout).
• Solid software engineering skills (e.g., Python and modern ML/CV frameworks) and experience working with real-world, noisy data.
• Ability to work in a dynamic, high-uncertainty environment, prioritize experiments, and iterate quickly.
• Ability to collaborate effectively with cross-functional teams and communicate complex technical topics clearly in English.