What are the responsibilities and job description for the Image & Video Synthesis AI Research Scientist position at EVONA?
Image & Video Synthesis AI Research Scientist
We are working with a fast-growing, innovative AI technology company focused on transforming ecommerce and fashion.
Role Overview
We are seeking a talented Image and Video Synthesis AI Research Scientist to join our team. In this role, you will design and implement advanced algorithms for high-quality image and video synthesis, style transfer, and editing.
Responsibilities
- Algorithm Development: Design and implement advanced algorithms for image and video synthesis using deep learning techniques, including GANs, diffusion models, neural style transfer, and monocular depth estimation.
- Model Training: Work with large datasets to train and optimize image synthesis models for generating high-quality, realistic images.
- Tool Development: Create tools and frameworks to streamline model development and deployment.
- Collaboration: Work with research scientists, engineers, and data scientists to integrate image and video synthesis models into larger systems.
- Troubleshooting: Debug and resolve issues with photo synthesis models as needed.
- Research Application: Stay current with the latest developments in image and video synthesis, applying them to practical challenges.
Requirements
- Education: Ph.D. in Computer Science, Electrical Engineering, or a related field, or 8 years of equivalent experience.
- Publications: Published in top-tier journals or conferences (e.g., CVPR, ICCV, ECCV, ICLR, NeurIPS, IJCV, TPAMI).
- Technical Skills: Proficient in Python with extensive experience in PyTorch; strong understanding of ML and deep learning concepts.
- Generative AI Experience: Experience with generative AI algorithms, such as GANs, diffusions, view synthesis, depth estimation, or style transfer.
- Problem-Solving: Strong analytical and troubleshooting skills.
- Communication: Ability to collaborate effectively in an English-speaking environment.
