Are you passionate about contributing meaningfully to battling cancer? Then join us here at MSK, where we can provide you with the opportunity to make a difference with your career. We believe this is a very exciting opportunity for someone who has the right skillset and drive to make an impact to support our mission here.
Machine learning and deep learning are changing how cancer patients are diagnosed and treated in modern hospitals. Computational Pathology leverages large-scale machine learning on high performance compute infrastructure to transform pathology from a qualitative to quantitative science. You will work in an exciting interdisciplinary environment with the potential to directly affect medical research, cancer care and patients lives.
For our computational pathology group, we are looking for a Machine Learning Scientist who will lead in the development, training and testing of Machine Learning. You will aid in the clinical assessment and understanding of cancer. The massive amount of digital pathology image data we see at MSKCC provides a rare opportunity within the field of computer vision and cancer research for conventional and unconventional modeling with clinical relevance, such as (semi-)supervised, weakly supervised and unsupervised machine learning methods.
Work and collaborate with a diverse team of machine learning experts, software engineers and medical doctors to build a new generation of artificial intelligence in cancer detection and treatment
Employ statistical methodologies on high volumes of data to tackle novel problems.
Build software and craft actionable insights.
Work at a high level of complexity in relation to image data, deep learning, and/or computational pathology and know statistical programming languages including but not limited to: R, Python, & Matlab.
Have the opportunity to demonstrate a modern compute cluster with hundreds of GPUs and the largest cluster of DGX nodes in the field.
Does your background match what we are seeking?
Doctorate in Computer Science with an emphasis on Machine Learning or Computer Vision.
An outstanding publication history in machine learning and/or computational pathology which includes a track record with established machine learning conferences, e.g., MICCAI, CVPR, ICML, etc.
Strong knowledge and background in machine learning, deep learning, computer vision and/or medical imaging, preferably in the pathology domain.
Experience in high performance computing (HPC).
Ability to excel working both independently and within a team, possessing a collaborative research mindset allowing them to work comfortably together with pathologists, AI researchers (same field and other fields), and computer scientists.
Ability to offer mentorship and guidance to others.
Interest in the independent development and testing of hypotheses and creative in finding both conventional and unconventional solutions, e.g., you dont stop with the outcome of a model, but also make interpretations and connect results with business needs.
Savvy at seeking deeper questions and exploring new approaches
Interest in medical data analysis
Maintains and improves professional growth and development through participation in scientific and technical discussions, workshops, and seminars to keep current with developments in web technology and computational tools
Internal Number: 2018-25274
About Memorial Sloan-Kettering Cancer Center
As one of the world's premier cancer centers, Memorial Sloan-Kettering Cancer Center is committed to exceptional patient care, leading-edge research, and superb educational programs. The close collaboration between our physicians and scientists is one of our unique strengths, enabling us to provide patients with the best care available today as we work to discover more effective strategies to prevent, control, and ultimately cure cancer in the future. Our education programs train future physicians and scientists, and the knowledge and experience they gain at Memorial Sloan-Kettering has an impact on cancer treatment and the biomedical research agenda around the world.