Columbia University Irving Medical Center / Vagelos College of Physicians and Surgeons
Machine Learning Scientist
Columbia University Irving Medical Center / Vagelos College of Physicians and Surgeons, New York, New York, us, 10261
Position Summary
The AlQuraishi Lab in the Departments of Systems Biology and Computer Science at Columbia University is seeking a Machine Learning Scientist with a focus on deep learning models for biomolecular systems and drug discovery. Projects span development and training of new neural network architectures, design of active learning experiments in conjunction with experimental collaborators, derivation of scaling laws for biomolecular systems, and other topics. All projects involve interactions with team members in the AlQuraishi lab as well as academic and industry partners in three major consortia: OpenFold, AISB (AI Structural Biology Network), and OpenBind. Responsibilities
High-level (dependent on specific scientific project): Design and train state-of-the-art neural network architectures for biomolecular systems, including prediction of protein-ligand, protein-protein, and antibody-antigen structures and affinities, and protein conformational ensembles. Design active learning algorithms and experiments to steer large-scale data acquisition campaigns focused on improving biomolecular models. Devise experiments to understand scaling behavior of biomolecular models. Curate and prepare datasets, and develop dataset processing algorithms, for in-acquisition and proprietary datasets, including in federated training settings. Day-to-day: Develop new ideas, write code, run experiments, analyze data, and prepare reports. Be an active member of one or more highly collaborative teams. Stay current with the ultrafast-paced nature of biomolecular machine learning. Maintain and enhance external visibility through publishing papers, writing open-source code, and engaging with the scientific community. Minimum Qualifications
M.S. in computer science / machine learning, computational biology, or related quantitative fields plus five years of related experience, or equivalent combination of education/experience. Preferred Qualifications
Ph.D. in computer science / machine learning, computational biology, or related quantitative fields. Extensive machine learning experience, including design, training, and deployment of complex neural architectures. Extensive programming experience in Python. Strong interpersonal skills, excellent written and verbal communication, and the ability to work effectively in cross-functional teams. Experience with scientific, and ideally biomolecular, machine learning. Knowledge of biology and biochemistry. Experience in high-performance computing including on-prem and cloud-based clusters. Compensation
Posting is for multiple projects with a broad range of required expertise levels. Salary range is $155k-230k/year depending on project and required experience level. Work location
In-person in New York, NY 10032 with option to work remotely 2-3 days per week.
#J-18808-Ljbffr
The AlQuraishi Lab in the Departments of Systems Biology and Computer Science at Columbia University is seeking a Machine Learning Scientist with a focus on deep learning models for biomolecular systems and drug discovery. Projects span development and training of new neural network architectures, design of active learning experiments in conjunction with experimental collaborators, derivation of scaling laws for biomolecular systems, and other topics. All projects involve interactions with team members in the AlQuraishi lab as well as academic and industry partners in three major consortia: OpenFold, AISB (AI Structural Biology Network), and OpenBind. Responsibilities
High-level (dependent on specific scientific project): Design and train state-of-the-art neural network architectures for biomolecular systems, including prediction of protein-ligand, protein-protein, and antibody-antigen structures and affinities, and protein conformational ensembles. Design active learning algorithms and experiments to steer large-scale data acquisition campaigns focused on improving biomolecular models. Devise experiments to understand scaling behavior of biomolecular models. Curate and prepare datasets, and develop dataset processing algorithms, for in-acquisition and proprietary datasets, including in federated training settings. Day-to-day: Develop new ideas, write code, run experiments, analyze data, and prepare reports. Be an active member of one or more highly collaborative teams. Stay current with the ultrafast-paced nature of biomolecular machine learning. Maintain and enhance external visibility through publishing papers, writing open-source code, and engaging with the scientific community. Minimum Qualifications
M.S. in computer science / machine learning, computational biology, or related quantitative fields plus five years of related experience, or equivalent combination of education/experience. Preferred Qualifications
Ph.D. in computer science / machine learning, computational biology, or related quantitative fields. Extensive machine learning experience, including design, training, and deployment of complex neural architectures. Extensive programming experience in Python. Strong interpersonal skills, excellent written and verbal communication, and the ability to work effectively in cross-functional teams. Experience with scientific, and ideally biomolecular, machine learning. Knowledge of biology and biochemistry. Experience in high-performance computing including on-prem and cloud-based clusters. Compensation
Posting is for multiple projects with a broad range of required expertise levels. Salary range is $155k-230k/year depending on project and required experience level. Work location
In-person in New York, NY 10032 with option to work remotely 2-3 days per week.
#J-18808-Ljbffr