Computer Vision Engineer (YOLO & Deep Learning)

Location: Remote
Employment Type: Full-time
Experience Level: Mid–Senior

About Us:
Wisy is an AI-powered platform that drives CPG growth by transforming fragmented retail data into clear, actionable insights. Our real-time AI agents enable brands to understand their market position, make faster decisions, and take timely action to stay ahead of the competition.

About the Role:
We are seeking a highly skilled Computer Vision Engineer with hands-on experience in YOLO-based object detection to help us scale our AI capabilities in complex, real-world retail environments.

This is an exciting opportunity to join a company on the cutting edge of applied AI and work alongside a high-caliber team of engineers, data scientists, and designers. Your work will directly influence Wisy’s impact and future trajectory.

Core Responsibilities (What You Will Do):

• Design, implement, and deploy YOLO-based object detection models for retail shelf and product imagery.
• Build end-to-end pipelines for image preprocessing, model inference, and postprocessing.
• Collaborate with backend, AI, and infrastructure engineers to integrate computer vision modules into Wisy’s broader AI platform.
• Optimize inference for real-time performance across both cloud and edge environments, balancing trade-offs between accuracy and efficiency in resource-constrained contexts such as low-end Android devices.
• Lead model evaluation using performance metrics (mAP, precision, recall, F1).
• Develop strategies for data labeling, quality control, and image annotation workflows.
• Conduct experiments using transfer learning, data augmentation, and model fine-tuning techniques.
• Implement best practices in version control, reproducibility, and MLOps.
• Create and maintain technical documentation and support onboarding of new team members.
• Contribute to sprint planning, estimations, and architecture discussions.
• Research and prototype emerging computer vision techniques to improve product accuracy and speed.
• Support internal tooling and developer experience as it relates to model deployment and visualization.
• Diagnose and troubleshoot performance issues in models and data pipelines.
• Ensure compliance with internal standards for security, data privacy, and operational excellence.

What We Value:

• Clarity & Simplicity – Writing clean, maintainable, and scalable code is a must.
• Bias for Action – You take initiative and move quickly, even with ambiguity.
• Collaboration Over Ego – You work well with others, seek feedback, and respect every perspective.
• Curiosity & Growth Mindset – You stay on top of industry trends and continuously improve your skills.
• Customer Obsession – You build with the end user in mind and align work to real outcomes.
• Trust & Transparency – You communicate openly and own your responsibilities.

What We Require (What We’re Looking For):

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
• 3+ years of hands-on experience in computer vision and deep learning.
• Proven experience with YOLOv5, YOLOv8, or similar object detection architectures.
• Proficiency in Python and frameworks such as PyTorch or TensorFlow.
• Familiarity with image annotation tools (e.g., CVAT, Label Studio) and labeling workflows.
• Experience with cloud platforms (AWS, GCP) and containerization (Docker, Kubernetes).
• Strong understanding of CNNs, training pipelines, and model evaluation strategies.

Nice to Have:

• Experience in the retail, logistics, or consumer goods industries
• Experience deploying models to mobile or edge devices