Research Scientist, Low Level Vision, Level 4

Overview

Snap Inc is a technology company focused on camera-enhanced experiences. Snap Research serves as an innovation engine, with projects ranging from solving hard technical problems to exploring new directions that can shift how people communicate and express themselves. The Computational Imaging Research Team in NYC focuses on enhancing user experiences with photo and short form video products, and enabling creators to make Lenses more easily in Lens Studio.

The 2025 focus areas include 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 vision-language models, and more.

• Propose and develop innovative technologies to improve image and video quality, such as (1) image/video super-resolution/restoration, (2) image/video quality assessment, or (3) advanced video codec

• Enhance the quality of AI-generated videos using low-level vision techniques, such as super-resolution and video frame interpolation

• Contribute to image editing, efficient vision-language model development, etc.

• Partner with product teams to deliver technologies to hundreds of millions of Snap chatters

• Work on projects including on-device neural network compression or non-NN methods speedup (optional)

• Mentor research interns, publish research at top academic conferences, or contribute to video compression standards

• Ability to identify and define impactful and challenging research and R&D projects in both academic and product contexts

• Ability to generate innovative research and engineering ideas through out-of-the-box thinking

• Strong prototyping, implementation, and programming skills (in Python and/or C++), including developing or accelerating NN methods (dataset preparation, architecture/loss design, and NN compression), or non-NN methods

• Ability to stay at the forefront of low-level vision or computational photography in academia

• Ability to remain at the cutting edge of advancements in the image/video quality industry

• Fast learner with the ability to quickly adapt to new topics such as image editing and efficient vision-language models

• Strong technical foundation in deep learning and computer vision

• Proven ability to lead and mentor interns, PhD students, and junior researchers, and to collaborate effectively with product teams

• Strong and clear communication skills

• PhD in a technical field such as computer science/electrical engineering, or equivalent years of experience

• Hands-on experience with state-of-the-art neural network techniques (e.g., CNNs, Transformers, GANs, diffusion models, VAEs, and/or other emerging techniques)

• Industry or academic experience in defining and solving research problems in low-level vision or computational photography, including image/video enhancement and assessment, video compression, image editing, or efficient vision-language modeling

• Hands-on experience with on-device NN compression (quantization, pruning, knowledge distillation, NAS, and related techniques)

• Successful publication record in top-tier academic conferences and journals (e.g., CVPR, ICCV, ECCV, ICLR, NeurIPS, SIGGRAPH, TPAMI) or contributions to video compression standards

• Strong technical foundation in signal processing, statistics, machine learning, and computer vision

• Hands-on experience with state-of-the-art non-NN methods in image processing and speedup on mobile devices (e.g., Metal for iOS, OpenGL or Vulkan for Android)

"Default Together" policy:
Snap values in-person collaboration and expects team members to work in an office 4+ days per week. Snap is an equal opportunity employer, committed to employment opportunities regardless of race, religious creed, color, national origin, ancestry, disability (physical or mental), medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, pregnancy, childbirth and breastfeeding, age, sexual…