Computer Vision Intern

Position Overview

• Location Type: Remote
• Employment Type: Full-Time
• Salary: Not specified

Reality Defender provides accurate, multi-modal AI-generated media detection solutions to enable enterprises and governments to identify and prevent fraud, disinformation, and harmful deepfakes in real time. As a Y Combinator graduate, Comcast NBCUniversal LIFT Labs alumni, and backed by DCVC, Reality Defender is the first company to pioneer multi-modal and multi-model detection of AI-generated media. Our web app and platform-agnostic API built by our research-forward team ensures that our customers can swiftly and securely mitigate fraud and cybersecurity risks in real time with a frictionless, robust solution.

Requirements

• PhD student in a relevant technical field
• Experience in computer vision
• Proficient in Python and in building deep learning models with PyTorch
• Published peer-reviewed research papers in reputable computer vision venues (e.g., CVPR, ICCV, NeurIPS)

Responsibilities

• Investigate new methods for generative image/video detection
• Collaborate with researchers in the team
• Perform research of deepfake image/video detection
• Write up results of research for internal reports and submission to academic journals/workshops
• Independently implement and evaluate ideas on modern deep learning stack - Python, PyTorch, and GPU-enabled cloud compute (like AWS/GCP)

About You

• Team player with a positive attitude and good communication skills
• Excited about our line of work

Company Information

• About Reality Defender: Reality Defender provides accurate, multi-modal AI-generated media detection solutions to enable enterprises and governments to identify and prevent fraud, disinformation, and harmful deepfakes in real time.
• Funding: Y Combinator graduate, Comcast NBCUniversal LIFT Labs alumni, and backed by DCVC.
• Technology: Web app and platform-agnostic API built with Python, PyTorch, and GPU-enabled cloud compute (AWS/GCP).
• Key Features: Best-in-class accuracy derived from research, near- or real-time detection across audio, video, image, and text modalities, easy-to-use API, intuitive web application, and platform-agnostic real-time audio detection.
• Privacy: Privacy-first, ensuring the strongest standards of compliance and keeping customer data away from the training of detection models.