Senior Research Scientist - 3D Vision

Santa Monica, CA 90401
Science – Research Science /
Hybrid
The most talked about AI company in Hollywood

Flawless is shattering the boundaries of traditional filmmaking with its groundbreaking suite of Gen AI film editing tools. Our mission is to empower filmmakers with cutting-edge technology that allows creativity without compromise, expands storytelling possibilities, and delivers unparalleled visual and emotional experiences.

What we are looking for:

As the Sr Research Scientist - 3D Vision you will be joining an innovative generative AI startup changing the future of filmmaking. The Sr Research Scientist - 3D Vision will report to the Chief Researcher, working closely with Science, VFX, Production, and Product teams. The Sr Research Scientist - 3D Vision will be responsible for leading a team of Research Scientist and Research Engineers for 3D Vision, Tracking and Reconstruction focused on delivering complex production level solutions in 3D Vision, and Audio Driven Facial Animation. This team is impacting the delivery for localization and foreign language dubbing solutions across feature films, episodic series, and commercial content. The Sr Research Scientist - 3D Vision must be a forward thinking, and solutions oriented leader and will be responsible for the innovation and development of generative AI editing solutions to our global clients. Critical to this role is having the ability to lead Publications, accepted at top-tier conferences like CVPR, ECCV, NeurIPS, and SIGGRAPH, as well as lead and mentor their research team of scientists, engineers and Interns. Excellent time-management skills, deep knowledge of the latest trends in immersive production, and experience in managing multiple projects in high volume on a global scale is imperative.  As senior leader; clear, concise, and constant communication is paramount to the success of our production ability.  This leader must be able to work effectively and efficiently with our cross-functional teams in both the US and UK locations. This position reports to the Chief Researcher, and works closely with other key production executives, creatives, and Science Leaders.

Qualifications

    • Minimum Qualifications 
    • Completed MSC (PhD preferred) in Visual Computing, Computer Vision, Computer Graphics or research industry experience with Deep Learning and Visual Computing 
    • 3+ Years of leadership, managing teams of 5+ Scientists/Engineers. 
    • 10+ Research experience with a strong publication record in top-tier CV and Graphics venues, such as Siggraph and CVPR 
    • Experience working in collaborative teams comprising researchers, applied and data scientists, and platform developers 
    • Ability to conduct proactive and independent research beyond expectations 
    • Remarkable background in linear algebra, statistical analysis 
    • Demonstrable experience with Deep Learning based models for virtual avatar reconstruction and animation 
    • Familiarity with modern 2D and 3D Vision (segmentation, tracking, 3D imaging) and advanced Computer Graphics (inverse and physics-based rendering, intrinsic image decomposition, shadow modeling) 
    • Experience with self-supervised and few-shot deep learning techniques. 
    • Experience with automated benchmarking and metrics methodologies 
    • Proficiency with Python and DL frameworks such as TensorFlow or PyTorch (preferred) 
    • Familiarity with differentiable rendering pipelines, such as Mitsuba, PyTorch3D or Taichi Graphics. 
    • Previous experience with cloud platforms, such as AWS, GCP, or Azure

Preferred Qualifications

    • Experience developing tools or solutions at scale for multi-modal or audio-aware 3D tracking systems in AR/VR or VFX 
    • Experience with C++ or CUDA 
    • Familiarity with CNN, Transformer, and GAN architectures 
    • Knowledge in Diffusion models and Volumetric Neural Rendering Comment end  
$200,000 - $250,000 a year