Principal Scientist of AI-Driven Protein design

Job Responsibilities

1. AI/ML-Driven Design: Lead the team in developing or utilizing state-of-the-art machine learning tools for de novo protein or antibody design; spearhead the development of novel antibody discovery methodologies.
2. Computational Tool Development: Develop or leverage open-source models, train them using internal datasets, fine-tune models as needed, and perform multi-parameter optimization of antibodies (e.g., affinity, selectivity, half-life, drug-like properties).
3. Cross-Functional Collaboration: Work closely with antibody engineering, structural biology, and therapeutic teams to translate AI predictions into physical molecules and effectively conduct wet lab validation.
4. Technology Exploration: Track breakthroughs in AI/ML and computational biology; lead external collaborations (e.g., with academia/AI companies) to build Innovent’s AI development ecosystem.
5. Strategic Leadership: Develop the team’s AI/ML technology roadmap, cultivate computational biology talent, and drive innovative molecular entities into the pipeline.

Qualifications

1.Education & Experience:

• Ph.D. in Computational Biology, Bioinformatics, Computer Science, or a related field, with a focus on AI/ML applications in life sciences; minimum 3 years of relevant experience.
• Experience in de novo protein design and antibody engineering is preferred.
• Prior success in leading AI/ML projects within pharmaceutical, biotech, or research institutions is highly desirable.
• Experience managing and developing ML/AI scientist teams; excellent communication skills to convey complex technical concepts to cross-functional colleagues; proven ability to collaborate effectively in interdisciplinary teams.

2.Technical Expertise:

• Deep knowledge of protein structure analysis, antibody biology, and therapeutic antibody design principles.
• Proficiency in protein modeling and structural analysis software (e.g., Rosetta, PyMOL, MOE, or equivalents).
• Extensive experience with generative AI; hands-on practice with cutting-edge ML tools (e.g., AlphaFold, RFdiffusion, ProteinMPNN, or similar models).
• Core competency in developing and implementing ML algorithms; proficiency in Python/R/C++ and deep learning architectures (e.g., CNNs, RNNs, Transformers).
• Expertise in advanced ML models for protein modeling, including generative models (diffusion, flow matching), language models (Transformers), multimodal learning, geometric deep learning, and graph representation learning.

3.Results-Driven:

• Published original research on AI applications in biomedicine in top-tier journals/conferences.
• Delivered presentations on AI/ML topics at conferences on behalf of companies or research institutions.