Manager, Mcicc

Merck Merck · Pharma · Shanghai, China

Manager role focusing on AI-driven drug evaluation and CADD, integrating AI and physics-informed approaches for small-molecule drug development. Responsibilities include designing, developing, and deploying AI systems, applying CADD methodologies, combining ML models with CADD workflows, and collaborating with cross-functional teams. Requires PhD/Master's in a related field with hands-on AI/CADD experience in drug discovery.

What you'd actually do

  1. Design, develop, and deploy AI‑powered systems for small‑molecule drug evaluation and development, integrating data from chemistry, biology, and structural modeling.
  2. Apply and extend CADD methodologies (e.g., structure‑based and ligand‑based approaches) to support drug design and evaluation.
  3. Combine machine learning models with CADD workflows, including virtual screening, molecular property prediction, binding/pose assessment, and developability evaluation.
  4. Collaborate closely with medicinal chemists, AI scientist, biologists, and project teams to translate scientific hypotheses and project needs into actionable computational strategies.
  5. Contribute to cross‑project AI/CADD platforms that enable scalable, reusable, and decision‑focused drug evaluation capabilities.

Skills

Required

  • PhD or Master’s degree with equivalent practical experience in CADD,Computational Chemistry, Computational Biology, AI, Machine Learning, or a related technical field.
  • Hands‑on experience in AI‑based small‑molecule drug evaluation or CADD‑related applications.
  • Solid understanding of small‑molecule drug discovery workflows, including hit identification, lead optimization, and decision checkpoints.
  • Strong experience with machine learning frameworks such as PyTorch, TensorFlow, or JAX, and scientific computing tools such as NumPy, SciPy, Pandas.
  • Experience working collaboratively with chemistry and biology scientists, with the ability to integrate domain knowledge into computational models.
  • Strong problem‑solving skills and the ability to learn quickly in a fast‑paced environment.
  • Excellent communication skills for cross‑disciplinary collaboration.

Nice to have

  • Practical expertise in CADD techniques, such as: Structure‑based drug design (e.g., docking, binding pose analysis), Ligand‑based modeling (QSAR, similarity, pharmacophore concepts), Physics‑informed or hybrid ML/physics approaches
  • Experience in AI models for drug discovery, including graph neural networks, generative models, structure prediction, or property prediction.
  • Experience in disease biology and target research, with demonstrated ability to link biological context to chemical design and evaluation strategies.
  • Familiarity with real pharmaceutical R&D decision processes, project milestones, and trade‑offs (e.g., potency vs. ADMET vs. developability).
  • Experience building tools or workflows that support project teams rather than stand‑alone research prototypes.

What the JD emphasized

  • AI‑driven drug evaluation
  • AI and physics‑informed computational approaches
  • AI‑powered systems for small‑molecule drug evaluation and development
  • machine learning models with CADD workflows
  • AI/CADD platforms

Other signals

  • AI-driven drug evaluation
  • AI and physics-informed computational approaches
  • AI-powered systems for small-molecule drug evaluation and development
  • machine learning models with CADD workflows
  • AI/CADD platforms