Postdoctoral Scientist, Deep Learning / Machine Learning - Drug Discovery

Johnson & Johnson - Cambridge, MA

Full-time - Entry Level

Remote - Cambridge, MA

Chemical Manufacturing

About the position

Johnson & Johnson Innovative Medicine is currently seeking a Postdoctoral Scientist, Deep Learning / Machine Learning to join our In Silico Drug Discovery team. The primary and preferred location is Cambridge, MA, with remote work options in the US considered on a case-by-case basis. At Johnson & Johnson, we believe health is everything. Our strength in healthcare innovation empowers us to build a world where complex diseases are prevented, treated, and cured, where treatments are smarter and less invasive, and solutions are personal. Through our expertise in Innovative Medicine and MedTech, we are uniquely positioned to innovate across the full spectrum of healthcare solutions today to deliver the breakthroughs of tomorrow, and profoundly impact health for humanity. For more than 130 years, diversity, equity & inclusion (DEI) has been a part of our cultural fabric at Johnson & Johnson and woven into how we do business every day. Rooted in Our Credo, the values of DEI fuel our pursuit to create a healthier, more equitable world. Our diverse workforce and culture of belonging accelerate innovation to solve the world's most pressing healthcare challenges. We know that the success of our business - and our ability to deliver meaningful solutions - depends on how well we understand and meet the diverse needs of the communities we serve. This is why we foster a culture of inclusion and belonging where all perspectives, abilities, and experiences are valued and our people can reach their potential. The successful candidate will contribute to a cutting-edge project that integrates quantum mechanics (QM) data with deep learning (DL) models to advance molecular predictive modeling. This role involves working closely with experts across various domains to develop innovative methods and tools that will enhance our drug discovery processes. The ideal candidate will have a strong background in deep learning and machine learning, with a keen interest in applying these skills to drug discovery. We are looking for a candidate with publications in high-level venues like NeurIPS, ICML, or ICLR, a background in drug discovery, demonstrated software skills, and knowledge of Python, PyTorch, and other DL-related tools. The candidate will be expected to collaborate effectively with cross-functional teams, contribute to the development of state-of-the-art methods, and ensure the reproducibility of experimental results. This is an exciting opportunity to be at the forefront of pharmaceutical innovation, leveraging advanced computational techniques to make a significant impact on healthcare.

Responsibilities

• Research and develop deep learning methods to effectively train graph neural networks for Quantum Mechanics and other physics informed data.
• Contribute to the creation of comprehensive reports and scientific publications documenting the methods and results of research projects.
• Publish findings in high-level conferences and journals.
• Participate in team meetings, brainstorming sessions, and collaborative projects to drive innovation and solve complex problems.
• Work closely with cross-functional teams, including data scientists, chemists, and biologists, to integrate deep learning models into the drug discovery pipeline.

Requirements

• PhD in machine learning, computer science, applied mathematics or relevant field (completed within the last 2 years, or expected to be completed in 2024) is required.
• Publications at top-tier Machine Learning conferences (i.e., NeurIPS, ICML, ICLR) are strongly preferred.
• Experience developing Deep Learning methods to train graph neural networks is required.
• Demonstrable expertise in developing deep neural networks (transformers, Bayesian neural nets, RNN, CNN) is required.
• Demonstrable expertise with Deep Learning frameworks, like PyTorch, Keras, Tensorflow is required.
• Demonstrable expertise in work with large datasets is required.
• Expertise in GPU computing is required.
• Ability to present and communicate with stakeholders is required.
• Ability to translate data into information and strategies into executable action plans is required.

Nice-to-haves

• Knowledge in Cheminformatics is desirable.

Benefits

• Medical insurance
• Dental insurance
• Vision insurance
• Life insurance
• Short- and long-term disability
• Business accident insurance
• Group legal insurance
• 401(k) retirement plan
• Vacation - up to 120 hours per calendar year
• Sick time - up to 40 hours per calendar year; for employees who reside in the State of Washington - up to 56 hours per calendar year
• Holiday pay, including Floating Holidays - up to 13 days per calendar year
• Work, Personal and Family Time - up to 40 hours per calendar year