This role pays less than
69%
of similar roles. Most pay
$161,862–$249,131
— the shaded band above.
At the midpoint, this role pays about
$180k
versus about
$205k
for comparable roles.
Based on 240 similar postings.
Employer
About Novartis
Novartis is a global biopharmaceutical company that researches, develops, manufactures, and markets prescription drugs in areas including oncology, immunology, neuroscience, and cardiology. Industry: Biopharmaceuticals
Novartis currently has
28 open roles
on FindRole.
Listed pay typically runs
$194,600–$361,400
across 28 roles with salary data.
The Computational Medicinal Chemist joins the Computer-Aided Drug Discovery team to drive medicinal chemistry efforts through structure-activity relationships, structure-based and ligand-based drug design, and predictive modeling for physical properties and pharmacokinetics. The role involves developing models from high-content and time-resolved screening data while leading cross-disciplinary mechanistic studies using physics-based modeling and simulation. This position focuses on the development of small molecules, peptides, RNAs, protein degradation, molecular glues, transient covalent inhibitors, and kinetic stabilization of drug-target complexes to improve clinical success rates. The candidate will utilize machine learning, active learning, and physics-based CADD methodologies within high-performance computing environments. Required expertise includes proficiency in tools like Schrodinger, CCG, and OpenEye, alongside skills in Python, data visualization, and statistical analysis to solve complex challenges in the drug discovery process for various therapeutic targets.
Design medicinal chemistry efforts using structure-activity relationships, structure-based design, and predictive methods for physical properties and pharmacokinetics.
Apply machine learning, active learning, and physics-based CADD methodologies to small molecule drug discovery and induced proximity space.
Integrate biological insights from scientific literature into lead characterization and screening initiatives.
Develop predictive models based on high-content and time-resolved screening data, including imaging techniques.
Generate hypotheses to improve clinical success rates for various modalities like peptides, RNAs, and protein degradation.
Lead cross-disciplinary mechanistic studies using physics-based modeling, biophysical characterization, and cellular validation.
Provide data visualization to communicate complex insights during the target identification and lead optimization processes.
What we're looking for
PhD in medicinal chemistry, computational chemistry, cheminformatics, computational biology, or a related field.
Candidates with laboratory backgrounds in chemistry and biology combined with strong computational experience are encouraged to apply.
2+ years of post-graduate experience in a drug discovery environment (preferred).
Proven track record of innovation through analogue design leading to significant impact on discovery projects (preferred).
Proficiency with computational drug design tools, high-performance computing environments, and a history of peer-reviewed publications.
Expertise in machine learning, active learning, and physics-based CADD methodologies for small molecule drug discovery.
Strong communication skills including data visualization, written, and oral communication to share insights.
Skills such as AI, Biostatistics, Python, Deep Learning, and Statistical Analysis are desired.
Cheminformatics
Data Science
Machine Learning
Artificial Intelligence
Python
SQL
Deep Learning
Generative AI
Linux
High-Performance Computing
Pandas
R
Data Visualization
Active Learning
Drug-Target Interaction Modeling
Free Energy Perturbation
Ligand Protein Docking
Python
R
Machine Learning
Data Science
High-Content Imaging
Cell Culture
Flow Cytometry
ELISA
Genomics
Cloud Computing
Large Language Models
Generative AI
Analytical Pipelines
Statistics
In Vitro Assays
Organ-on-Chip
Remote (Foster City, CA)17 days ago
$169,320–$219,120
Python
PyTorch
JAX
Machine Learning
Deep Learning
Generative Modeling
Protein Language Models
Foundation Models
Geometric Neural Networks
AlphaFold
Active Learning
Multimodal Learning
Representation Learning
Data Integration
Design-Build-Test-Learn