About

• About the Role
• We are seeking a highly motivated Applied Research Scientist to join our Applied Research team, reporting to the Head of Applied Research. The successful candidate will focus on advancing generative media research, with a primary emphasis on image models, while also contributing across video, audio, and 3D modalities.
• In addition to core research, this role will work directly with customers, alongside our Revenue and Sales teams, to design, fine-tune, and deploy custom models, workflows, and creative assets tailored to industries such as E-commerce, VFX, and other visual media. This is a hands-on position at the intersection of cutting-edge research and real-world application.
• Responsibilities
• Collaborate with the Applied Research team to develop state-of-the-art generative media solutions, with a strong emphasis on image models.
• Fine-tune and extend UNet and DiT architectures for generative tasks across multiple modalities (image, video, audio, 3D).
• Work directly with customers to research, design, and deliver customized models, workflows, and creative assets for applications in E-commerce, VFX, and other visual media sectors.
• Implement and adapt novel techniques from research papers and repositories into practical, high-quality code.
• Curate, preprocess, and design high-quality datasets for training and fine-tuning.
• Collaborate cross-functionally with Product, Engineering, and Commercial teams to ensure smooth integration of models into customer workflows.
• Stay at the cutting edge of generative modeling research, incorporating advancements into both internal pipelines and customer-facing solutions.
• Evaluate, benchmark, and optimize models for quality, diversity, and efficiency in generative media applications.
• Qualifications
• Proven experience with image models; knowledge of video, audio, or 3D generative models is a strong plus.
• Strong experience fine-tuning UNet and DiT architectures for generative tasks.
• Proficiency in Python, with the ability to implement and customize code from research repositories.
• Solid understanding of machine learning concepts (formal ML background preferred but not required).
• Experience with Linux, CUDA, and PyTorch in a research or production setting.
• Demonstrated ability to create customer-specific generative solutions and workflows.
• Experience managing fine-tuning processes to improve model quality and diversity.
• Portfolio, GitHub, or prior work showcasing generative media or applied ML research, particularly in E-commerce, VFX, or other visual media contexts, is highly desirable.
• Equal Employment Opportunity
• We are an equal opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability, or other legally protected statuses.