Senior AI Scientist

About the Role

We are looking for an experienced Senior Data Scientist to join our AI Platform team and build AI-driven drug discovery technologies.

This role is responsible for end-to-end development, including data processing, model development, model training, inference deployment, platform integration, and testing.

The ideal candidate should have a background in biomedical sciences, pharmacy, pharmacology, medicinal chemistry, bioinformatics, computational chemistry, computer science, or related fields, with strong programming skills and hands-on experience in machine learning or deep learning. We are looking for someone who can independently develop projects from raw data to model inference and platform implementation.

What You'll Do

1. Develop AI algorithms for structure-based drug design, small molecules, peptide drugs, and biomedical applications.
2. Build and optimize deep learning, geometric deep learning, and reinforcement learning models for drug discovery.
3. Design AI workflows covering data preparation, featurization, model training, inference, validation, deployment, and testing.
4. Integrate datasets such as PDB, ChEMBL, PubChem, UniProt, and other biomedical or chemical databases.
5. Prepare training-ready datasets, including data cleaning, molecular representation, protein / ligand feature encoding, and quality control.
6. Develop reliable, scalable, and production-quality Python code for AI platform applications.
7. Work with drug designers, medicinal chemists, software engineers, and project teams to translate scientific needs into AI models.

Minimum Qualifications

1 Master's degree or above in biomedical sciences, pharmacy, pharmacology, medicinal chemistry, bioinformatics, computational chemistry, computer science, or a related field.
2. 3+ years of hands-on experience in biomedical AI, AI drug discovery, computational chemistry, molecular modeling, structure-based drug design, or scientific machine learning.
3. Strong proficiency in Python and experience with PyTorch or similar deep learning frameworks.
4. Experience with deep learning and/or reinforcement learning.
5. Experience in at least one of the following: 3D molecular modeling, protein-ligand modeling, molecular simulation, structure-based drug design, molecular property prediction, or molecular representation learning.
6. Solid understanding of statistics, probability, machine learning fundamentals, and model evaluation.
7. Experience with Git and maintainable software development.
8. Ability to independently develop projects from data processing to model inference.

Nice to Have

1. Knowledge of SE(3)-equivariant models, geometric deep learning, graph neural networks, or 3D rotation-aware modeling.
2. Experience with offline reinforcement learning, SAC, hierarchical reinforcement learning, or related RL methods.
3. Familiarity with Linux, HPC, GPU computing, cloud computing, or large-scale computing environments.
4. Experience debugging, profiling, and optimizing Python or C++ code.
5. Strong domain knowledge in biochemistry, medicinal chemistry, pharmacology, or drug discovery.
6. Experience with molecular datasets such as PDB, ChEMBL, PubChem, UniProt, or BindingDB.
7. Experience building APIs, model inference services, internal AI tools, or reproducible ML pipelines.