Senior Machine Learning Engineer (Video Understanding)

Location: Zurich; flexible office, hybrid, or home working, with remote work support across Switzerland, Finland, Poland, the UK, Italy, and Germany. Candidates must be eligible to work in the hiring location.

Company

hirify.global develops computer vision technology that automates workflows and provides actionable insights for delivery, healthcare, and retail businesses.

What you will do

• Lead technical discovery and early development of a computer vision system for retail operational insight and automation.
• Define and prioritize experiments addressing precision, recall, latency, and other key risks in real-world retail environments.
• Design and implement end-to-end CV/ML pipelines covering video ingestion, preprocessing, model training, evaluation, and deployment.
• Set up and refine human annotation workflows for high-quality video training and test datasets.
• Select, adapt, and optimize computer vision architectures for suspicious behavior and human action detection in unconstrained environments.
• Collaborate with product managers, engineering leaders, data teams, and external stakeholders to shape technical roadmaps and best practices.

Requirements

• University degree in Computer Science, Electrical Engineering, Mathematics, or a related technical field.
• Significant hands-on experience designing, training, evaluating, and deploying computer vision and machine learning models in production.
• Proven experience building end-to-end CV/ML systems from 0 to 1, preferably commercial products rather than purely academic projects.
• Strong expertise in video-based pipelines and human action or behavior recognition.
• Hands-on experience with vision transformers for temporal video understanding.
• Solid software engineering skills, including Python and modern ML/CV frameworks, plus experience working with noisy real-world data.
• Ability to work in a dynamic, high-uncertainty environment, prioritize experiments, and iterate quickly.
• Ability to collaborate with cross-functional product, backend, data, and operations teams and communicate complex technical topics clearly in English at B2 level or higher.
• Eligible to work in the hiring location.

Nice to have

• Advanced degree in a relevant technical field.
• Experience fine-tuning Vision-Language Models.
• Experience with privacy-aware or GDPR-compliant video data pipelines.
• Experience building or selecting annotation tools and workflows for computer vision training data.
• Prior work in retail or autonomous stores using computer vision.

Culture & Benefits

• Highly skilled team and a people-first culture.
• Flexible office, hybrid, or home working.
• Hackathons, global team outings, and company celebrations.
• Birthday day off.
• Individual equity plan in a high-growth company.
• Hybrid-optimized offices in Zurich, Warsaw, Tampere, and London, with location-specific benefits.