Assistant or Associate Project Scientist - Department of Electrical Engineering and Computer Sciences

The Department of Electrical Engineering and Computer Sciences, in the College of Engineering, at the University of California, Berkeley welcomes applications for an Assistant or Associate Project Scientist in Professor Yun Song's group. The Song Lab focuses on the intersection of machine learning, statistics, and biology. Their research leverages advanced mathematical and computational models to analyze large-scale genomic data and understand complex biological processes.
The successful candidate will conduct independent and collaborative research to advance PEINT (Protein Evolution IN Time), a generative AI framework for modeling protein sequence evolution.
Core Responsibilities:

• Method Development: Developing new machine learning methods to model evolutionary dynamics, focusing on extending PEINT to more complex biological settings.
• Computational Research: Designing and implementing computational algorithms, developing and evaluating large-scale models, and conducting rigorous benchmarking.
• Experimental Collaboration: Collaborating with experimental researchers to validate model predictions and generated protein sequences.
• Mentorship: Mentoring and assisting in the supervision of graduate and undergraduate students, as well as other junior researchers.
• Project Coordination: Coordinating collaborative research activities and contributing to the preparation of grant proposals, technical reports, and progress reports for funding agencies.
• Dissemination: Preparing manuscripts for publication in peer-reviewed journals and presenting research findings at scientific conferences.

Labor Contract
:
https://ucnet.universityofcalifornia.edu/resources/employment-policies-contracts/bargaining-units/academic-researchers/contract/

Basic qualifications

(required at time of application)
Ph.D. or equivalent international degree.

Preferred qualifications

• Demonstrated research experience in developing advanced machine learning methods for biological sequence modeling, particularly protein sequence evolution
• Expertise in deep learning architectures and modern generative modeling techniques
• Experience integrating evolutionary principles into machine learning models, including modeling evolutionary dynamics along phylogenetic trees.
• Proficiency in scientific programming and large-scale computational model development
• Experience evaluating models using biological sequence and functional data
• A strong record of original research as evidenced by peer-reviewed publications

Document requirements

Curriculum Vitae - Your most recently updated C.V. (including a full publication list).
Cover Letter
Statement of Research

Reference requirements

3 required (contact information only)

Apply link:

https://aprecruit.berkeley.edu/JPF05632

Help contact:

cwelden@berkeley.edu