Computer Vision Engineer

Invisible AI is building an end-to-end computer vision platform that digitizes the physical world using AI-enabled edge cameras. The Computer Vision Engineer will research, develop, optimize, test, and deploy computer vision and deep learning solutions for real-time perception on edge platforms, while collaborating across teams and documenting technical processes.

Responsibilities:

• Lead the research, design, and implementation of computer vision algorithms including but not limited to algorithms for detection, segmentation, and tracking human poses and objects in the scene, 3D reconstruction from multiple views, etc
• Fine tune and deploy LLMs & VLMs on on-prem GPU clusters running local models
• Develop and train end-to-end deep learning models that can run on Nvidia Jetson edge compute platforms
• Work on data pre-processing, augmentation, and cleaning to ensure high-quality input data for the computer vision models
• Optimize algorithms and models for real-time or near-real-time processing, taking into account efficiency and resource constraints
• Collaborate with other teams to integrate computer vision solutions into our products and systems
• Develop robust testing procedures and validation frameworks to ensure the accuracy and reliability of our computer vision systems
• Stay up-to-date with the latest advancements in computer vision and machine learning, and apply cutting-edge techniques to our projects
• Document code, algorithms, and processes to facilitate knowledge sharing and collaboration within the team