Develop ML/DL algorithms for image reconstruction, restoration, enhancement, and understanding, incorporating physical models and optical-system constraints.
Investigate generative AI and diffusion models for imaging applications, including physically informed image reconstruction and synthesis.
Design and conduct optical experiments, simulations, and algorithmic prototypes to validate research hypotheses and optimize imaging performance.
Collect and analyze experimental image and video data, connecting laboratory measurements with simulation and model evaluation.
Collaborate with optical, sensor, and algorithm teams to assess system-level trade-offs and translate research into practical imaging solutions.
Stay current with research in electro-optics, computational imaging, physics-informed learning, and computer vision.
Document and present research outcomes internally and in global collaboration meetings.
Skills and Qualifications
M.Sc. or advanced-stage PhD candidacy, in Physics, Applied Physics, Electro-Optics, Optical Engineering, Electrical Engineering, or a closely related field, with research focused on optics or imaging.
Strong background in both electro-optics and physics, demonstrated through academic research or relevant industry experience.
Solid theoretical knowledge of wave and geometrical optics, diffraction, optical image formation, and light–sensor interactions.
Hands-on experience with optical or electro-optical systems, including experimental setup, measurement, characterization, and analysis.
2–5 years of relevant research experience in electro-optics, computational imaging, or physics-based imaging, in academia or industry.
Practical experience applying machine learning, computer vision, or deep learning to imaging problems.
Understanding of deep learning architectures relevant to imaging, such as CNNs, transformers, or generative models.
Proficiency in scientific programming and numerical analysis using Python and/or MATLAB, with experience in a deep learning framework such as PyTorch or TensorFlow.
Ability to independently design experiments, interpret physical phenomena, and connect theoretical models with measured results.
Excellent communication and collaboration skills in a multidisciplinary R&D environment.
Preferred Qualifications
Experience in computational photography, inverse imaging problems, or joint optimization of optical systems and reconstruction algorithms.
Experience with camera systems, CMOS image sensors, optical-system characterization, or imaging-system calibration.
Familiarity with optical simulation and design tools such as Zemax or Code V.
Experience with physics-informed learning, differentiable imaging models, or simulation-to-real methods.
Experience with diffusion models or other generative approaches for image restoration, enhancement, or synthesis.
Publications in relevant optics, imaging, computer vision, or machine learning venues.
Our Offering
A chance to work on cutting-edge electro-optical, computational imaging, and AI technologies that influence Samsung’s products worldwide.
Exposure to world-class researchers and engineers in a collaborative, innovation-driven environment.
Access to advanced computing resources and imaging labs.
Flexible engagement suited to an advanced-stage PhD student or postdoctoral researcher.
Mentorship, professional growth, and the opportunity to contribute to high-impact global R&D projects.
Please note that, throughout the interview process, we ask all candidates to refrain from sharing any confidential, proprietary, or trade-secret information belonging to their current or former employers or any other third party. We are interested in your skills, experience, and accomplishments, and ask that you describe them without disclosing information that is not yours to share.
Please visit Samsung membership to see Privacy Policy, which defaults according to your location. You can change Country/Language at the bottom of the page. If you are European Economic Resident, please click here.
