REQUIREMENTS:

• Proficiency in programming languages: C#, Python and Java.
• Experience with YOLO and other object detection frameworks.
• Experience in real-time image processing and optimization.
• Experience with GPU acceleration and CUDA programming.
• C++ knowledge will be preferred.
• Strong knowledge of OpenPose, OpenCV, and Mediapipe.
• Knowledge of cloud-based ML deployment.
• Understanding of edge ML and embedded systems.
• Prior experience in ML model training and fine-tuning.
• Familiarity with deep learning frameworks such as TensorFlow or PyTorch.
• Strong aptitude in picking up (operation knowledge) in more than one types of system.
• Strong problem solving and analytical skills.

OVERVIEW OF ROLE:

The Vision Analytics Engineer is a skilled Developer with experience in OpenPose, OpenCV, and Mediapipe.
He/She is to have strong expertise in image processing and proficient in YOLO or other ML(Machine Learning) frameworks for image and object recognition.
The role involves developing, integrating with OpenPose/Mediapipe and creating/optimizing machine learning models for real-time applications.

RESPONSIBILITIES:

• Develop and implement computer vision application using OpenPose, OpenCV, and Mediapipe.
• Utilize YOLO or other ML based techniques for image and object recognition.
• Optimize image processing pipelines for performance and accuracy.
• Develop adaptors/interfaces for ML models into applications.Collaborate with cross-functional teams to deploy solutions.