The Computer Vision Intern will investigate new methods for generative image and video detection.
The intern will collaborate with researchers within the team to enhance the research efforts.
Responsibilities include performing research on deepfake image and video detection.
The intern will write up results of research for internal reports and for submission to academic journals and workshops.
The role requires independently implementing and evaluating ideas using a modern deep learning stack, including Python, PyTorch, and GPU-enabled cloud computing platforms like AWS or GCP.
Requirements:
Candidates must be a PhD student in a relevant technical field.
Experience in computer vision is required for this position.
Proficiency in Python and in building deep learning models with PyTorch is necessary.
Applicants should have published peer-reviewed research papers in reputable computer vision venues, such as CVPR, ICCV, or NeurIPS.
The ideal candidate should be a team player with a positive attitude and good communication skills.
A genuine excitement about the company's line of work is essential.
Benefits:
The position offers the opportunity to work with a research-forward team that is pioneering multi-modal and multi-model detection of AI-generated media.
Interns will gain hands-on experience in a cutting-edge field focused on fraud and disinformation detection.
The role provides a chance to contribute to impactful research that may be published in academic journals and workshops.
Interns will have access to advanced tools and technologies, including GPU-enabled cloud computing resources.
The company promotes a privacy-first approach, ensuring compliance and data security in its operations.
