Computer Vision Data Scientist (YOLO / PyTorch / OpenCV)

Overview

We are looking for an experienced Data Scientist to join AIQ's computer vision team, dedicated to developing and optimizing AI models that enhance our video analytics platform. In this position, you will collaborate closely with machine learning engineers and data annotators to transform experimental models into robust, deployment-ready solutions for industrial video applications.

Key Responsibilities

• Develop and optimize computer vision models for object detection, tracking, and segmentation using PyTorch, TensorFlow, and OpenCV.
• Work hands-on with advanced architectures such as YOLO, RF-DETR, and Vision-Language Models (VLMs), adapting and fine-tuning them for AIQ’s specific use cases.
• Manage image and video dataset preparation including curation, preprocessing, and augmentation while maintaining strong communication with the annotation team.
• Train, fine-tune, and assess model performance based on stringent metrics like mAP, precision, and recall, iterating until desired accuracy is achieved.
• Utilize experiment tracking tools such as MLflow or Weights & Biases to monitor progress and results.
• Implement model optimization methods including TensorRT and ONNX, considering constraints inherent in real-world deployments.

Required Qualifications

• Bachelor’s or Master’s degree in Computer Science, Data Science, Machine Learning, or related fields.
• 3 to 7 years of practical experience in machine learning with a specialization in computer vision.
• Proficiency in Python programming and practical expertise using PyTorch or TensorFlow alongside OpenCV.
• Hands-on experience with detection, tracking, and segmentation neural networks like YOLO and RF-DETR.
• Experience tuning Vision-Language Models is a plus.
• Knowledge of experiment tracking systems and model optimization workflows.