Senior Scientist Computational Chemistry

MSD•Upper Gwynedd Township, PA

1d•$129,000 - $203,100•Onsite

About The Position

Merck is seeking a creative, self-motivated computational chemist and data scientist to join the Modeling and Informatics group at its West Point, Pennsylvania site. The group uses predictive sciences, AI/ML, and structure-based drug design to support therapeutic discovery and collaborates with Discovery and Process Chemistry teams across the global network. This hybrid-function role combines direct early discovery project support (approximately 50%) with data science and machine learning model design and deployment (approximately 50%). The successful candidate will apply advanced computational techniques to active drug discovery programs and develop methods, algorithms, and predictive tools to address foundational drug-design problems. The position is on-site and is not remote.

Requirements

PhD in Computational Chemistry, Chemoinformatics, Chemistry, Data Science, or equivalent, with a computational or data science emphasis.
Proficiency in molecular modeling techniques, including docking, molecular simulation, homology modeling, quantum mechanics, and ligand- and structure-based design, as well as a Linux environment.
Proficiency in scientific Python programming, such as RDKit, OpenEye toolkits, Pandas, NumPy, and SciPy.
Hands-on experience applying machine learning, statistical modeling, or deep learning to chemical, biological, or physical datasets, using tools such as scikit-learn, PyTorch, or TensorFlow.
Ability to communicate, collaborate, and deliver results as a member of multidisciplinary teams.
Strong desire to learn and innovate.
Ability to manage multiple priorities across project delivery and method development.
Strong oral and written communication skills, including the ability to explain complex ML and computational concepts to non-specialists.
Evidence of creative application of computational approaches to pharmaceutical problems.
Track record of recent publications and/or presentations and external presence.

Nice To Haves

Demonstrated impact on molecule design in a biopharmaceutical or biotechnology industry environment.
Expertise with commercial modeling software packages such as Schrödinger, MOE, or OpenEye.
Experience with modern software development practices, including Git/GitHub, Docker containerization, and cloud environments such as AWS or Google Cloud.
Experience developing and deploying interactive data visualization applications or web tools such as Spotfire.
Familiarity with generative AI for de novo molecule generation, geometric deep learning, or large language models for scientific data.
Experience with automated workflow orchestration tools such as KNIME or Pipeline Pilot.

Responsibilities

Serve as the primary computational chemistry partner on multidisciplinary discovery teams, supporting candidate design and optimization.
Design molecules using computational drug discovery techniques, including structure- and ligand-based design, molecular docking, conformational sampling, molecular dynamics, and quantum mechanics.
Conduct informative data analysis, multi-parameter optimization, and molecular visualization.
Design protein constructs and assess binding-site ligandability.
Design ligand libraries, perform virtual screening, and conduct targeted library enumeration.
Translate computational hypotheses and model predictions into actionable synthetic targets for medicinal chemistry teams.
Communicate computational insights to chemistry and adjacent-function teams to inform project decisions.
Partner with the Data Science team to design, build, benchmark, and deploy predictive AI/ML models for molecular property, ADMET, and potency prediction.
Develop and deploy automated computational workflows and reusable Python cheminformatics and structural modeling toolkits and pipelines.
Explore and implement machine learning methods, including generative chemistry models, active learning, and foundation models for molecular design.
Collaborate with Cheminformatics, Data Science, and IT teams to scale computational chemistry tools and integrate models into enterprise software platforms.
Establish best practices for scientific code versioning, reproducible data analysis, and model validation.
Share knowledge and reusable workflows and contribute to colleagues' success and departmental wellbeing.
Mentor colleagues in emerging data science techniques and modern computational workflows.