Computer Vision Engineer

About the job
We are looking for a Computer Vision Engineer to join our team and help push the boundaries of AI-driven object detection, segmentation, and pose estimation. If you have a passion for working with cutting-edge models like YOLO and have delivered industry-level solutions, we’d love to hear from you!
Responsiblities:

Develop and optimize computer vision models for real-world applications, including object detection, segmentation, and pose estimation.
Implement ML pipelines for model training, evaluation, deployment, and post-production improvements based on user feedback.
Work on Visual Language Models (VLMs) to develop advanced vision-based analysis—understanding what’s happening in videos and assessing the severity of events.
Deploy models on production servers, optimize for scalability, and improve system performance. Collaborate with the AI/ML team to continuously enhance model accuracy and robustness.
Collaborate with AI, engineering, and product teams to integrate models into our smart security and surveillance solutions.

What We're Looking For

Strong expertise in object detection, segmentation, and pose estimation.
Experience with YOLO, Detectron, Mask R-CNN, and other industry-standard models.
Hands-on experience with ML pipelines for vision models, from training to deployment and retraining based on real-world feedback.
Deep understanding of VLMs (Visual Language Models) and ability to develop event analysis solutions from videos.
Proficiency in Python, TensorFlow, PyTorch, OpenCV and related frameworks.
Experience in deploying models in cloud-based and edge environments.
Hands-on experience in deploying models on production servers and optimizing performance.