Postdoctoral Researcher – Video Understanding
Janssen Research & Development LLC, a Johnson & Johnson company, is recruiting a Postdoctoral Researcher to join the Video Understanding team. The role involves designing, implementing, and evaluating AI/ML methods for frame‑level and video‑level understanding across diverse medical modalities, including endoscopy, ultrasound, and magnetic resonance enterography (MRE). The position is available in the US or Europe, with remote arrangements considered.
Key Responsibilities
* Conceive, develop, and implement AI‑tool ideas with internal clinical personnel to address needs around endoscopy.
* Design, develop, and evaluate deep learning models for medical video and image understanding (scoring, segmentation, detection).
* Lead research and development of uncertainty quantification methods for model predictions (e.g., Bayesian approaches, ensembles, calibration metrics, predictive intervals) and integrate uncertainty estimates to quantify reliability and confidence of AI‑driven diagnostic outputs.
* Develop advanced multi‑modal models for video analysis, integrating data from endoscopy, ultrasound, intestinal ultrasound (IUS), and MRE.
* Clearly articulate highly technical methods and results to diverse audiences and partners to drive decision‑making.
* Participate in cross‑functional team meetings, lead discussions and follow‑up questions, and compile answers into briefing reports.
* Extract insights from briefing reports focusing on the business value of AI pipelines for immunology.
Required Qualifications
* Ph.D. in a quantitative discipline (Physics, Mathematics, Computer Science, Electrical Engineering, or similar).
* Extensive experience driving research and applying Computer Vision techniques (Transformers, CNNs, RNNs, GANs).
* Proven expertise in uncertainty model and measures development for deep learning.
* Experience with state‑of‑the‑art techniques for video understanding (foundational models, transformers).
* Proficiency with programming languages such as Python or C++.
* Experience with traditional Computer Vision applications (OpenCV, object detection, edge detection, image segmentation).
* Experience with machine‑learning algorithms (random forest, SVM, boosting, neural networks).
* Strong publication record and ability to effectively communicate technical work to a wide audience.
Preferred Qualifications
* Domain knowledge and experience with medical videos such as endoscopy.
* Experience with medical imaging modalities including ultrasound, IUS, and MRE.
* Experience applying or adapting foundation/self‑supervised pretraining for medical domains (e.g., DINOv2, contrastive methods).
* Familiarity with clinical trial workflows, regulatory considerations, and working with clinical partners.
* Experience with multimodal AI and exposure to drug discovery and clinical development processes.
* Experience working closely with healthcare professionals.
* Thriving in a diverse, inclusive culture.
Johnson & Johnson is an Equal Opportunity Employer, affirming the importance of diversity and inclusion. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, age, national origin, protected veteran status and will not be discriminated against on the basis of disability.
#J-18808-Ljbffr