We are seeking a passionate and talented Postdoctoral Researcher to advance the field of applied machine learning in the context of human genetic data. This individual will conceive and execute analyses clarifying the application of natural language processing models to diverse aspects of early biological target discovery and evaluation while embedded within a collaborative academic/biotech setting. Using large-scale transformer neural networks to model the effects of protein coding variation in the human genome, the successful candidate will lead the development of novel methodology to characterize disease relevance and lay the foundations for an ultra-high throughput experimental framework.

This position is supported by the Maze Advanced Analytics Fellowship Program, which provides funding and scientific engagement to scholars interested in applied research bridging academic and industrial applications. The candidate will be jointly supervised by Dr. Vasilis Ntranos at UCSF and the Data Sciences group at Maze Therapeutics, and will work as part of a cross-functional team comprised of Data Scientists, Functional Genomic Scientists, Human Geneticists, and Computational Chemists to facilitate highly multidisciplinary early discovery research.

ABOUT THE NTRANOS LAB:

The Ntranos lab is developing computational methods at the intersection of information theory, genomics, and machine learning, with a particular focus on single-cell technologies and alternative splicing. Their research revolves around key algorithmic and statistical challenges that arise in computational biology and is highly collaborative, spanning multiple biological domains in immunology, human genetics, and cancer biology. The Ntranos lab is integrated within the broader computational research community at UCSF as part of the Dept. of Epidemiology & Biostatistics, the Diabetes Center, the Dept. of Bioengineering & Therapeutic Sciences, and the Bakar Computational Health Sciences Institute.    

QUALIFICATIONS:  

• Ph.D. in Computer Science, Bioinformatics, Mathematics/Statistics, or similar disciplines
• Strong critical thinking, experimental design, programming, and data analysis skills
• Knowledge of common machine learning algorithms and methods for analyzing high-dimensional data
• Familiarity with basic machine learning workflows and computational modeling applications is required; expertise strongly preferred
• Experience working with modern neural network architectures such as transformers, autoencoders, attention models etc.
• Familiarity with state-of-the-art machine learning approaches applied to biological sequence data (e.g., in the context of protein prediction tasks) is strongly preferred
• Enthusiasm for cross-functional collaboration in a highly multidisciplinary intellectual environment
• Excellent communication, presentation, collaboration, and organizational skills
• Experience with computational chemistry, computational biology, and/or cloud computing applications strongly preferred