ZipRecruiter
Job Description
Position Summary
Med Chem AIDD Group Leader (Principal Scientist), will lead a team of computational chemists and AI scientists dedicated to applying and developing advanced computational methods to accelerate the company's small molecule drug discovery projects. This role requires not only deep technical expertise to personally solve key scientific problems but also the ability to effectively manage a team, plan project-level computational strategies, and collaborate closely with experimental teams to drive progress from target to PCC.
Key Responsibilities
Team Leadership & Management:
Lead and mentor a team of 2-4 computational scientists, responsible for task allocation, scientific guidance, and team members' career development. Project Scientific Leadership:
Serve as the core computational lead on multiple small molecule discovery projects, designing, executing, and overseeing project computational strategies, including target assessment, virtual screening, and lead optimization. Cross-Functional Collaboration:
Establish close partnerships with Medicinal Chemistry, Structural Biology, DMPK, and Pharmacology teams to ensure efficient integration of computational work with experimental design and data analysis, thereby driving the DMTA cycle. Technology Innovation & Method Development:
Track and evaluate the latest technological advances in the CADD/AIDD field; lead the development, validation, and deployment of new computational workflows and predictive models to address specific project challenges. Communication of Results:
Clearly and accurately communicate computational results and strategic recommendations to project teams and management, ensuring that computational insights are effectively translated into project decisions. Basic Qualifications Ph.D. in Computational Chemistry, Cheminformatics, or a related field. 5+ years of experience in small molecule drug discovery within the pharmaceutical or biotechnology industry. Solid programming skills in Python and experience with relevant scientific computing libraries. Extensive hands-on experience in both structure-based (SBDD) and ligand-based (LBDD) drug design. Qualifications Physics-based Simulations & Free Energy Calculations:
Extensive hands-on experience with advanced physics-based methods, such as free-energy perturbation (FEP), relative binding energy calculations, and QM/MM simulations for mechanism of action studies. Machine Learning & AI Applications: A proven track record of developing, validating, and deploying bespoke machine learning models for QSAR, ADMET prediction, and activity prediction. Familiarity with modern AI architectures and their application in chemistry, such as
Graph Neural Networks (GNNs), Transformer models, and Active Learning
strategies. Experience applying
generative AI models
for property-guided molecular design or scaffold hopping. Cheminformatics & Data Analysis:
Expertise in large-scale cheminformatics analysis, including library design, analysis, and mining of large datasets from High-Throughput Screening (HTS), DNA-Encoded Library (DEL), and fragment screening campaigns. Breadth & Depth of Project Experience: Proven success in applying computational methods to support project progression across various target classes (e.g.,
kinases, GPCRs, ion channels, nuclear receptors ). Practical project experience supporting novel drug modalities such as
covalent inhibitors, protein degraders (PROTACs), molecular glues, and cyclic peptide .
#J-18808-Ljbffr
Lead and mentor a team of 2-4 computational scientists, responsible for task allocation, scientific guidance, and team members' career development. Project Scientific Leadership:
Serve as the core computational lead on multiple small molecule discovery projects, designing, executing, and overseeing project computational strategies, including target assessment, virtual screening, and lead optimization. Cross-Functional Collaboration:
Establish close partnerships with Medicinal Chemistry, Structural Biology, DMPK, and Pharmacology teams to ensure efficient integration of computational work with experimental design and data analysis, thereby driving the DMTA cycle. Technology Innovation & Method Development:
Track and evaluate the latest technological advances in the CADD/AIDD field; lead the development, validation, and deployment of new computational workflows and predictive models to address specific project challenges. Communication of Results:
Clearly and accurately communicate computational results and strategic recommendations to project teams and management, ensuring that computational insights are effectively translated into project decisions. Basic Qualifications Ph.D. in Computational Chemistry, Cheminformatics, or a related field. 5+ years of experience in small molecule drug discovery within the pharmaceutical or biotechnology industry. Solid programming skills in Python and experience with relevant scientific computing libraries. Extensive hands-on experience in both structure-based (SBDD) and ligand-based (LBDD) drug design. Qualifications Physics-based Simulations & Free Energy Calculations:
Extensive hands-on experience with advanced physics-based methods, such as free-energy perturbation (FEP), relative binding energy calculations, and QM/MM simulations for mechanism of action studies. Machine Learning & AI Applications: A proven track record of developing, validating, and deploying bespoke machine learning models for QSAR, ADMET prediction, and activity prediction. Familiarity with modern AI architectures and their application in chemistry, such as
Graph Neural Networks (GNNs), Transformer models, and Active Learning
strategies. Experience applying
generative AI models
for property-guided molecular design or scaffold hopping. Cheminformatics & Data Analysis:
Expertise in large-scale cheminformatics analysis, including library design, analysis, and mining of large datasets from High-Throughput Screening (HTS), DNA-Encoded Library (DEL), and fragment screening campaigns. Breadth & Depth of Project Experience: Proven success in applying computational methods to support project progression across various target classes (e.g.,
kinases, GPCRs, ion channels, nuclear receptors ). Practical project experience supporting novel drug modalities such as
covalent inhibitors, protein degraders (PROTACs), molecular glues, and cyclic peptide .
#J-18808-Ljbffr