Senior Scientist, Computer Vision & AI (m/w/d) - #2109423

Are you passionate about computer vision and deep learning? Do you aspire to leverage your expertise in the discovery and development of cancer biomarkers? At AstraZeneca Computational Pathology, we're seeking a Senior Scientist to join our Computer Vision and AI team. In this pivotal role, you'll have the opportunity to develop cutting-edge computer vision algorithms specifically designed for the analysis of digital pathology images. Your contributions will directly impact our Oncology portfolio by advancing the discovery of novel biomarkers. Be a part of our quest to push the boundaries of cancer treatment and make a meaningful difference in the lives of patients worldwide.

About Astrazeneca

AstraZeneca is a global, science-led, patient-focused biopharmaceutical company that focuses on the discovery, development and commercialisation of prescription medicines for some of the world’s most serious diseases. But we’re more than one of the world’s leading pharmaceutical companies.

Site Description

Join us at one of AstraZeneca's over 400 global sites, nestled in the vibrant city of Munich. Here at Computational Pathology Munich, we pride ourselves on fostering a collaborative environment where everyone is encouraged to be their genuine selves. We believe that bringing your full self to work is essential, and we're committed to supporting your well-being. To help you thrive, we offer a variety of benefits. Our bright and spacious workspace is designed with sustainability in mind. Our networking events connect you with like-minded professionals and our family and childcare support ensure a balanced lifestyle. Munich is not only a vibrant and multicultural city, it also offers stunning natural beauty in its surroundings, with the majestic Alps and numerous lakes nearby for hiking, biking, swimming and skiing adventures.

BUSINESS AREA

From diagnosis to later stage development, we are focused on leading the way forward to create innovative solutions that transform lives. We are focused on identifying and treating patients earlier, where there is greater curative potential. With the greatest number of early stage cancer trials in the industry, we are getting closer to finding cures every day.

What You’ll Do

• Research, develop and release latest artificial intelligence methods to improve on the accuracy and the few-shot capability of our current image analysis methods as well as to extend our current AI-based biomarker analysis capabilities.
• Applying such methods, build research use only (RUO) image analysis solutions for the retrospective analysis of clinical datasets to inform drug and biomarker development programs.
• Disseminate knowledge, best practices and developed algorithms and software tools to internal audiences via project meetings, seminars and documentation as well as to the external academic community with conference presentations and journal publications
• Collaborate closely with project stakeholders and interfacing functions such as biomarker development, pathology, quality assurance, data management, software development, data science and bioinformatics.
  
  
  

Essential For The Role

• Ph.D. degree in computer sciences, mathematics, physics, bioinformatics or comparable degree; or equivalent experience e.g. M. Sc. and ≥ 2-3 years working experience on machine learning and computer vision in industry.
• Advanced knowledge of state-of-the-art deep learning models and architectures for computer vision, including experience working on weakly supervised learning and/or semantic / instance / panoptic segmentation.
• Good programming skills in Python and good knowledge of the most common scientific computing libraries (e.g. NumPy, pandas, scikit-learn, SciPy, OpenCV) and machine learning frameworks (PyTorch, torchvision).
• Knowledgeable of best practices for software development (e.g. docstring, unit testing, CI pipelines, Gitlab/GitHub) as well as for the development, validation and release of models (e.g. data splitting, model testing, hyperparameter tuning)
• Proven track record of scientific publications, conference contributions in field of machine learning and/or medical image processing (e.g. MICCAI, MIDL, ISBI) and/or delivered AI solutions in scientific industry projects.
• Talent to conceptualize, build, communicate and implement novel scientific ideas aligned with the drug development and biomarker strategies
  
  
  

Beneficial for the role

• Working experience with digital pathology and/or medical (e.g. PET / MRI / CT) images
• Working experience with at least one of the following: foundation models, transformers, semi-supervised learning, self-supervised learning, generative AI (e.g. GAN / Diffusion models).