Data Science, Cheminformatics & AI: Lab-in-the-Loop Hit Finding
Novartis
August 06, 2026
On-site
San Diego, CA
Clinical Research and Development
Role Responsibilities:
- Locally lead and execute data science strategy for Lab-in-the-Loop (LitL) workflows to accelerate low-molecular-weight therapeutic discovery; champion model development/deployment best practices, including monitoring and prediction telemetry.
- Develop and execute in silico hit-finding strategies using internal and external compounds from ultra-large virtual (Make-on-Demand) chemical spaces; apply best-practice computational tools to accelerate/diversify hits.
- Use in silico approaches (e.g., cheminformatics, generative AI, Make-on-Demand chemistry) with internal multimodal data (structure, chemogenomics, gene expression, imaging) to drive early hit-finding impact; develop cutting-edge methods (e.g., agentic workflows, drug–target interaction modeling).
- Design and implement scalable, robust data pipelines for high-throughput assay data to enable automated, reproducible hit-finding workflows.
Essential Requirements:
- PhD in cheminformatics or chemistry (or related degree) with demonstrated applicable experience.
- 4+ years post-graduate experience applying cheminformatics, data science, and ML to hit finding in early drug discovery.
- Experience with hit-finding technologies (e.g., high-throughput screening and/or advanced phenotypic screening).
- Excellent scientific communication and data visualization.
- Ability to work in interdisciplinary teams with proactive, results-oriented communication; promotes mutual respect and positivity.
- Strong experience in Linux HPC and/or cloud environments.
- Proficiency in Python scientific ecosystem; agentic coding approaches; reproducible research practices (version control, testing, documentation); databases and SQL.
- Experience implementing AI in Lab-in-the-Loop / iterative / self-driving lab workflows.
- Experience with Make-on-Demand and virtual spaces such as Enamine REAL.
Desirable Requirements:
- Orchestrating agents/tools and physical automated screening workflows.
- Building/integrating workflows into agentic systems for drug discovery.
- Track record turning in silico approaches into reproducible, generalizable hit-finding workflows.
- Familiarity with ligand–protein docking, generative chemistry, active learning, drug–target interaction modeling, and/or free energy perturbation.
- Peer-reviewed publications and/or conference presentations.
- Locally lead and execute data science strategy for Lab-in-the-Loop (LitL) workflows to accelerate low-molecular-weight therapeutic discovery; champion model development/deployment best practices, including monitoring and prediction telemetry.
- Develop and execute in silico hit-finding strategies using internal and external compounds from ultra-large virtual (Make-on-Demand) chemical spaces; apply best-practice computational tools to accelerate/diversify hits.
- Use in silico approaches (e.g., cheminformatics, generative AI, Make-on-Demand chemistry) with internal multimodal data (structure, chemogenomics, gene expression, imaging) to drive early hit-finding impact; develop cutting-edge methods (e.g., agentic workflows, drug–target interaction modeling).
- Design and implement scalable, robust data pipelines for high-throughput assay data to enable automated, reproducible hit-finding workflows.
Essential Requirements:
- PhD in cheminformatics or chemistry (or related degree) with demonstrated applicable experience.
- 4+ years post-graduate experience applying cheminformatics, data science, and ML to hit finding in early drug discovery.
- Experience with hit-finding technologies (e.g., high-throughput screening and/or advanced phenotypic screening).
- Excellent scientific communication and data visualization.
- Ability to work in interdisciplinary teams with proactive, results-oriented communication; promotes mutual respect and positivity.
- Strong experience in Linux HPC and/or cloud environments.
- Proficiency in Python scientific ecosystem; agentic coding approaches; reproducible research practices (version control, testing, documentation); databases and SQL.
- Experience implementing AI in Lab-in-the-Loop / iterative / self-driving lab workflows.
- Experience with Make-on-Demand and virtual spaces such as Enamine REAL.
Desirable Requirements:
- Orchestrating agents/tools and physical automated screening workflows.
- Building/integrating workflows into agentic systems for drug discovery.
- Track record turning in silico approaches into reproducible, generalizable hit-finding workflows.
- Familiarity with ligand–protein docking, generative chemistry, active learning, drug–target interaction modeling, and/or free energy perturbation.
- Peer-reviewed publications and/or conference presentations.