Research Scientist, Animation Direction, Level 4

OverviewSnap Inc. is a technology company focused on camera-based experiences. We are looking for a Research Scientist to join the Computational Imaging Research Team in NYC. The team enhances user experiences with photo and short-form video products and enables creators to make Lenses more easily in Lens Studio. Our 2025 focus includes improving image and video quality (quality assessment, video super resolution, compression, image editing) and animations (animation generation, 3D avatar, video generation for animations). Research areas include computer vision, computational imaging/photography, 3D motion/video generation, efficient large language models, and more.What you'll doPropose and develop cutting-edge multimodal techniques for 3D human animation and video generation — enabling expressive Bitmoji avatars and next-gen Snapchat video generation experiencesBuild models that map text, audio, video, and music to 3D animation and drive downstream tasks such as background video generation for animation rendering and audio-driven lip-synced video generationAdvance avatar technologies including animatable 3D Gaussian avatars, head/body reconstruction, and animation controlCollaborate with product teams to deploy research at scale and publish at top-tier academic venuesKnowledge, Skills & AbilitiesAbility to define impactful research problems and deliver practical solutions, both in academic and product contextsDeep expertise in human motion modeling, facial/body animation, and generative modeling (e.g., text-to-motion, text-to-image, text-to-video)Familiarity with video generation, avatar representations (e.g., mesh, NeRF, Gaussian), and rendering pipelinesStrong prototyping and engineering skills (Python, PyTorch, C++), with experience in large-scale distributed ML training on GCP/AWSProven ability to lead and mentor interns, PhD students, and junior researchers, and to collaborate effectively with product teamsExcellent communication and cross-functional collaboration skillsMinimum QualificationsPhD in a technical field such as Computer Science or Electrical Engineering, or equivalent experienceHands-on experience with mainstream generative models (Diffusion, Transformers, GANs, VAEs) for animation or videoResearch or product experience in 3D human motion generation, image/video generation, 3D avatar reconstruction and animation, or multimodal generationPreferred QualificationsPublications in top-tier venues (e.g., CVPR, SIGGRAPH, NeurIPS, ICCV, ECCV, ICLR) or contributions to open-source projectsExperience with large-scale dataset curation and distributed ML model training for image/video generationStrong foundation in computer vision, 3D graphics, and multimodal learningPolicies & Benefits"Default Together" policy: Snap expects team members to work in an office 4+ days per week. Snap is an equal opportunity employer and provides employment opportunities regardless of race, color, religion, sex, disability, age, or other protected status in accordance with applicable laws. EOE, including disability/vets. If you require accommodations, please contact Benefits: Snap offers paid parental leave, comprehensive medical coverage, mental health support, and compensation benefits aligned with Snap’s long-term success. For accommodations or disability-related needs, please use the provided pensationIn the United States, pay is organized into zones with ranges set by location. The base salary ranges are:Zone A (CA, WA, NYC): $173,000-$259,000Zone B: $164,000-$246,000Zone C: $147,000-$220,000This position is eligible for equity in the form of RSUs. The starting pay is determined by skills, experience, location, and market conditions and may be negotiable within the stated range.Additional resources: A Decade of Snap; CitizenSnap; The DEI Innovation Summit; Snap News; Applicant and Candidate Privacy Policy. #J-18808-Ljbffr

Created: 2025-09-30