<p><strong>Scandit Germany</strong></p> <p><strong>Senior Computer Vision/Machine Learning Engineer - Video/Action Recognition </strong></p> <p>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.</p> <p>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 <strong>Senior Computer Vision Engineer</strong>, 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.</p> <p>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.</p> <p>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.</p> <h2><strong>About the role</strong></h2> <p>As a <strong>Senior Computer Vision/Machine Learning Engineer</strong>, 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, privacy-aware computer vision models that can operate in live retail environments.</p> <p>This role connects cutting-edge CV/ML research with real-world product constraints – requiring both deep technical expertise and a pragmatic, experimental approach to building production-ready systems under ambiguity and time pressure.</p> <p><strong>What you will do</strong></p> <ul> <li>Defining and prioritizing technical experiments to validate key risks (e.g. precision, recall, latency) for computer vision models in retail stores</li> <li>Designing and implementing end-to-end CV/ML pipelines on real-world video data, from data ingestion and preprocessing through model training, evaluation, and deployment</li> <li>Setting up and refining the human annotation workflow to create high-quality training and test datasets from video streams</li> <li>Collaborating with product managers and engineering leaders to clarify requirements, align on milestones, and translate business needs into technical roadmaps</li> <li>Selecting, adapting, and optimizing state-of-the-art computer vision architectures for suspicious behavior and action detection in unconstrained environments</li> <li>Providing technical leadership in the space of video-based computer vision applications, helping shape best practices and future hiring for the team</li> </ul> <h2><strong>Who you are</strong></h2> <p>We are looking for a senior computer vision / machine learning engineer who has successfully built and shipped real-world products, ideally involving action recognition on video. You combine deep hands-on technical expertise with a pragmatic, experimental mindset and are comfortable working in a high-ambiguity, 0→1 product environment. You should enjoy collaborating closely with product and engineering stakeholders, shaping the technical direction, and iterating quickly on ideas to validate the riskiest assumptions.</p> <ul> <li>University degree in Computer Science, Electrical Engineering, Mathematics or a related technical field (advanced degree is a plus but not mandatory)</li> <li>Significant hands-on experience in computer vision and machine learning, including designing, training, evaluating and deploying models in production</li> <li>Proven track record of building end-to-end CV/ML systems from 0→1 (ideally commercial products rather than purely academic projects)</li> <li>Strong expertise with video-based pipelines and human action or behavior recognition (e.g. retail, autonomous checkout or similar domains). </li> <li>Hands-on experience with vision transformers for temporal video understanding. Experience fine-tuning Vision-Language Models (VLMs) is a strong plus.</li> <li>Solid software engineering skills (e.g. Python and modern ML/CV frameworks) and experience working with real-world, noisy data</li> <li>Ability to work in a dynamic, high-uncertainty environment, prioritize experiments, and iterate quickly on technical approaches</li> <li>Ability to collaborate effectively with cross-functional teams (e.g. product, backend, data, operations) and communicate complex technical topics clearly in English (B2 level or higher)</li> <li>Eligible to work in the hiring location</li> </ul> <p>Nice to have:</p> <ul> <li>Experience with privacy-aware or GDPR-compliant data pipelines, especially for video data</li> <li>Background in building or selecting annotation tools and workflows f