We are seeking a talented Computer Vision / ML researcher to join our team. The job will focus on developing innovative deep learning solutions for efficient video restoration in new imaging systems. You will be part of an interdisciplinary team developing technologies that will shape future our products.
Deep learning development:
Design, implement, and optimize deep learning models for various tasks in the field of video restoration. Implement and validate models using various datasets.
Prepare, filter, process, and analyze large-scale datasets to train and evaluate models.
Analyze the results of your algorithm and compare with other leading methods.
Optimize models for real-time performance and resource efficiency.
Research:
Investigate efficient architecture patterns (lightweight backbones, attention mechanisms, recurrent designs) suitable for on-device inference.
Explore how algorithm approaches can mitigate artifacts of new imaging systems.
Stay updated with recent advancements in the field.
Collaboration:
Work closely with ML researchers, SW, HW and camera architecture engineers to translate research ideas into robust models and practical systems.
Requirements: Minimum Qualifications
Strong foundation in image processing, computer vision, machine learning, and deep learning.
Proficiency in Python and deep learning frameworks (e.g. PyTorch).
Hands on demonstrated experience with designing real time deep learning solutions, using large scale datasets.
Proficiency in Python and deep learning frameworks (e.g. PyTorch).
Experience with model evaluation, debugging, experimental analysis, and failure analysis.
PhD or Master's degree in Computer Science, Electrical Engineering, in related research fields.
Proficient in both written and verbal communication.
Ability to work both autonomously and collaboratively.
PhD or Master's degree in Computer Science, Electrical Engineering in related research fields.
5+ or more years of relevant experience.
Preferred Qualifications
Experience with video restoration, super-resolution, denoising, deblurring, artifact removal, inverse problems or computational imaging.
Experience with advanced implementation architectures on GPU, Dedicated HW or Neural engines.
Experience with generative priors (diffusion, flow matching) is an advantage.
Background in signal processing, physics, computational imaging or inverse problems.
Publications in top-tier computer vision conferences (CVPR, ICCV, ECCV, NeurIPS).
This position is open to all candidates.