Principal Scientist Machine Learning

Profile

Bristol-Myers Squibb is a global Biopharma company committed to a single mission: to discover, develop, and deliver innovative medicines focused on helping millions of patients around the world in disease areas such as oncology, cardiovascular, immunoscience and fibrosis.

Join us and make a difference. We hire the best people and provide them with a work environment that places a premium on diversity, integrity, collaboration and personal development. Through a culture of inclusion, we create a better, more productive work environment. We believe that the diverse experiences and perspectives of all our employees help to drive innovation and transformative business results.

Role Outline

This role will provide collaborative, creative, and interdisciplinary applied machine learning research in partnership between Informatics & Predictive Sciences (IPS) and Chemistry organizations.

Reporting to the lead for Predictive Drug Substance Research, scenarios will involve a range of datasets and learning objectives, including for example drug discovery, structural biology, multi-modal modeling and prediction for chemical and biological datasets.


Formulation and implementation of predictive modeling and machine learning solutions for the optimization of chemical structures and properties.

Application of cutting-edge machine learning (deep learning) approaches to structural biology and molecular interaction challenges.

Design and generation of integrated chemical and biological data assets for predictive research in partnership with internal and external collaborators.


The successful candidate will work alongside experts in familiar applications of machine learning in the biotechnology domain, including:


Collaboration to develop human-in-the-loop systems to capture and operationalize machine learning datasets and algorithms used by BMS scientists.

Application of supervised, self-supervised, semi-supervised deep learning methods to derive robust generalizable and reusable representations for chemical and biological assay data.

Design of multi-task, multi-modal and generative neural network learning approaches to tackle real-world drug discovery optimization problems, including prediction of both assayed and abstract compound properties.

Contribution to design and development of Machine Learning data repositories focused on proteins and chemical compounds.


The position requires an individual with demonstrated scientific leadership potential and excellent communication and collaboration skills. Keen interest and hands-on expertise in the inter-disciplinary application of advanced machine learning methods to biotechnology research scenarios are imperative.

Responsibilities

Responsibilities include but are not limited to:


Pursue leading research in applied machine learning that demonstrates the value of predictive methods to accelerate and optimize drug development.

Derive and apply predictive approaches in collaboration with BMS colleagues in the Informatics and Predictive Sciences, and Chemistry departments.

Apply rigorous internal standards for applied machine learning practice, including evaluation of methods, approaches and solutions.

Contribute to broader data analysis and predictive methods strategies across the business as required, including assessment of 3rd party capabilities.

Present strategies, approaches, results and conclusions to BMS colleagues and external audiences.

Contribute to enable strategic collaborations with academic and commercial collaborators to benefit therapeutic programs.


Background experience & complementary knowledge


PhD in Computer Science, Electrical Engineering, or related field.

At least 5 years of experience of applied machine learning research, preferably in university or biotechnology research environments.

Substantial publication track record of applied ML approaches to solve complex predictive problems, with focus on cheminformatics applications.

Proven experience in development and application of novel algorithmic approaches to optimize processes and/or accelerate data-driven decisions.

In-depth knowledge of contemporary machine learning, pattern recognition and data-mining techniques, paradigms and application scenarios.

Expertise in more than one of the following key areas:

ANNs and Large-margin Classifiers, including CNN, RNN and Attention Models.

Generative Neural Network Models

Deep Reinforcement Learning

Probabilistic methods, incl. Gaussian Process Classifiers

Ensemble methods

Active, Transfer & Semi-supervised learning

Optimization, density estimation& outlier detection.





Demonstrable commitment to rigorous practice in reproducible research.

Hands-on experience of data integration, mining & visualization, and development of multivariate models in the chemical R&D context.

Strong knowledge of contemporary data and computing infrastructures, open-source analytics tools, e.g. TensorFlow or PyTorch

Proven problem-solving skills, collaborative nature and adaptability across disciplines.

Excellent verbal and written communication skills, ability to convey complex subject matter to lay audiences. Fluent verbal and written English language skills prerequisite.


*The position can be located in our Cambridge, MA or San Diego, CA office.

Bristol-Myers Squibb recognizes the importance of balance and flexibility in our work environment. We offer a wide variety of competitive benefits, services and programs that provide our employees the resources to pursue their goals, both at work and in their personal lives.

Bristol-Myers Squibb is an equal opportunity employer. Qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability or protected veteran status.

Company info

Sign Up Now - WashingtondcCrossing.com