About the role
Job Description: Video Knowledge Engineer
Are you passionate about Computer Vision, Gen AI, and ready to dive into a thrilling project that blends cutting-edge technology with the vibrant world of entertainment? Were seeking a skilled Computer Vision Knowledge Engineer to participate in building an AI platform that revolutionizes how we create, curate, and deliver short-form content. You'll work alongside product, engineering, AI, and machine learning experts to build real-world AI systems that shape the future of entertainment. This role is ideal for someone who thrives at the intersection of Gen AI, machine learning, and software engineering, with a passion for building innovative AI products.
Responsibilities:
* Coordinate with internal teams and vendors to identify and implement optimal metadata and video knowledge extraction solutions for the AI platform, enabling effective creation, curation, and delivery of short-form content. * Collaborate with internal stakeholders and external vendors to evaluate, utilize, and enhance computer vision tools and libraries, ensuring robust video content analysis and metadata extraction. * Work closely with the team, partners and vendors to design and implement computer vision algorithms that extract actionable insights and high-quality metadata from video content. * Partner with DevOps and engineering teams to integrate computer vision models and metadata extraction solutions into scalable, containerized environments using Docker and Kubernetes. * Engage with data scientists, machine learning engineers, DevOps, and vendors to deliver cohesive, scalable solutions for video knowledge extraction and metadata optimization.
Qualifications/Requirements:
* Proficiency in Python. * Solid experience with development and deployment tools, including containerization (Docker, Kubernetes) and workflow orchestration (Temporal or similar). * Familiarity with video analysis tools and libraries such as OpenCV, FFmpeg, or similar. * Experience in computer vision algorithms, preferably with broad familiarity and use of existing tools and libraries (e.g., OpenCV, PySceneDetect) for building CV applications. * Expertise in multiple areas listed below:
* Object and people detection (must) * Facial recognition (must) * Image and video segmentation * Activity recognition * Video summarization * Video identification * Video behavior analysis
Preferred Qualifications:
* Practical knowledge of artificial neural networks for computer vision, especially in Convolutional Neural Networks (CNNs). * Exposure to deep learning frameworks such as TensorFlow or PyTorch. * Expertise in any additional CV areas listed below:
* Edge detection * Style detection * Gesture recognition * Video tracking * Object co-segmentation
Originally posted on Himalayas