Scientist, Next Generation Medicine Design

Key Skills

Aartificial intelligence, C Programming, C++, Data Analysis, Data Visualization, Design, Effective communication skills, Java Programming, Machine learning techniques, Perl Programming, Python Programming

Job Description

Bristol Myers Squibb encompasses a broad range of disciplines to enable a robust pipeline of drug candidates aimed at serious diseases. Chemistry is a core capability in Small Molecule & Drug Discovery with innovative scientists working in medicinal chemistry, radiochemistry, analytical chemistry, and large-scale synthesis. Within SMDD our Lead Discovery and Optimization (LDO) team is responsible for high throughput screening, compound storage and distribution, primary assays to support discovery programs, and compound profiling to explore drug liabilities in vitro. LDO scientists discover and adopt cutting edge assay technologies that utilize state-of-the-art automation to drive speed and efficiency. Our Molecular Structure and Design team embraces novel approaches to computer-aided drug design, machine learning, and structural biology. The integration of these disciplines provides a seamless and highly interactive environment for discovery scientists to learn, develop, and innovate. Working in partnership with our disease area experts in the Thematic Research Centers provides an exciting pathway to discover and deliver medicines to patients in need.

Traditional targets and modalities that have provided rich substrates for medicine design and decades of productive industrial and academic research are not the primary targets of the future. There is a slow but steady shift in the target and modality landscape. Novel modalities such as protein degradation is an intense and hot area of scientific research.

We are seeking exceptional scientific leaders who have high energy, have high capacity to work in a rapid and fluid research environment, innately curious and pro-active leaders with versatile skills, to join the Molecular Structure & Design team with a focus on driving our Protein Homeostasis portfolio of projects. As part of our team, you would utilize structure-based and ligand-based computational chemistry methods combined with data visualization, data analysis, machine learning and AI techniques to design molecules with superior degradation and pharmacological properties.

In collaboration with multi-disciplinary Protein Degrader project teams, you will be expected to proactively lead projects, generate testable hypotheses, lead/design/execute complex computational experiments, provide in-depth analysis and interpretation of results, and translate them into actionable molecular designs that advance the discovery portfolio. Through close collaboration, clear communication, and technical excellence, you will work with scientists across the R&D organization to influence the pipeline from target identification and degrader optimization through to candidate nomination.

Responsibilities will include, but are not limited to, the following:

• Lead and influence the prospective use of computational methods in rigorously evaluating therapeutic targets, protein degradation modality and degrader designs within project teams.
• In close collaboration with project teams, develop and apply a wide variety of design and computational methods to improve potency, selectivity, protein degradation profiles and ADME properties while minimizing toxicological risk and pro-actively influence decision making on project teams.
• Significantly enhance understanding of SAR and contribute to team strategy by assimilating and interpreting data using structural modeling, AI/ML, statistical and data-mining/data-visualization technologies.
• Develop and apply new approaches for designing bioactive-relevant features using multi parameter optimization methods.
• Pro-actively provide scholarship in early target space vis-à-vis competitive information, literature/patent reviews and mining, chemical matter feasibility assessment, target feasibility/modality assessment, druggability/binding site characterizations, as appropriate.
• Maintain and develop working knowledge of contemporary computational chemistry methods and their application to discovery projects.

Scientific/Technical/Functional Skills:

• Demonstrated skills in the application of computer-assisted drug design using standard modeling and computational software packages
• Demonstrated ability to independently analyze literature and project data, formulate creative design hypotheses, data analysis and design novel agents in the context of project need.
• Demonstrated ability to serve as a lead computational chemist on multiple discovery projects and be accountable for delivery of project goals
• A working knowledge of medicinal chemistry and discovery
• Basic programming experience in at least one scripting language (e.g., Perl, Python) or programming language (Java, C, C++)

• Excellent communication and organizational skills and ability to work within a multidisciplinary team across geographic areas to advance discovery projects are required
• Personal attributes of integrity, creativity, problem solving, and strong work ethic

Basic Qualifications:

Bachelor’s degree with 5+ years of Academic or Industry experience

or

Master’s Degree with 3+ years of Academic or Industry experience

or

PhD and no years of experience

Preferred Qualifications:

• A completed Ph.D. in computational chemistry or a related field with strong application background as demonstrated by contributions to leading journals
• Demonstrated expertise in a subset of computational methods: docking methods, molecular dynamics simulations, homology modeling approaches, free energy simulations, AI/machine learning techniques, statistical methods, large-scale data visualization/analysis and multiple parameter optimization methods and a familiarity with the rest.
• Demonstrated experience in applying computational methods to diverse biological targets such as different protein families, DNA, RNA using different modalities such as traditional modulators, allosteric modulators, covalent agents, chimeric protein degraders, molecular glues, antibodies, antibody-drug conjugates is preferred.