Adobe is looking to build the next generation of creative tools, specifically in video understanding and generation, to advance the creativity world through features in Adobe's products and reach millions of people worldwide.
Requirements
- Strong proficiency in Python and PyTorch
- Solid foundation in computer science fundamentals
- Experience with distributed training and its common strategies
- Experience in state-of-the-art Generative AI technologies, such as VLMs and diffusion models
- Strong hands-on experience working on image/video understanding, generation and editing
- Working with large-scale datasets
- Good publication record in Computer Vision, AI/ML or related fields
Responsibilities
- Develop and implement scalable and efficient modeling algorithms that can work with large-scale data in production systems
- Develop and fine-tune (e.g., ViTs, VLMs, multimodal encoders) large-scale foundation models for video understanding and generation
- Collaborate with extraordinary researchers and engineers to bring research ideas to production
- Convert a research idea/paper to code in Python and typical machine learning development toolkits
- Stay on top of the latest ML research (e.g., diffusion models, alignment methods, multimodal understanding) and translate advances into practical solutions
Other
- Masters or Ph.D. in Computer Science, AI/ML or related fields
- Excellent communication skills
- Adobe will consider qualified applicants with arrest or conviction records for employment in accordance with state and local laws and “fair chance” ordinances
- Adobe is proud to be an Equal Employment Opportunity employer
- Adobe aims to make Adobe.com accessible to any and all users
