Senior Scientist, AI/ML for Protein Design

About Us
Evercrisp Biosciences is a well-funded Bay Area biotechnology company focused on the discovery and development of targeted intracellular genome-editing CRISPR therapeutics in multiple disease areas. Evercrisp is applying advanced computational methods, machine-learning and protein engineering to deliver novel enzymes with high cell uptake and in vivo editing.

Evercrisp’s computational team is seeking a creative and motivated expert in machine learning for macromolecular design. As a Senior Scientist, the ideal candidate will leverage their fluency with modern machine learning frameworks and collaborate with experimental teams to build ML models of biological macromolecules and enhance Evercrisp’s gene editing platform.

About the Position
The Sr. Scientist will also be in charge of utilizing existing biological datasets, curating custom datasets for internal experimentation, and analyzing structural & biophysical characteristics of protein sequences to enable an iterative design-test-learn cycle. The successful candidate will help grow Evercrisp’s computational capabilities and produce candidate molecules for in vitro and in vivo evaluation.

Responsibilities:

• Develop and apply ML models to solve the needs and challenges specific to delivery of novel protein-based CRISPR therapeutics.
• Enhance ML model performance by incorporating biological & physical features of macromolecules.
• Work with biologists and biochemists to acquire appropriate datasets to maximize predictive capabilities of machine learning models from limited datasets.
• Understand and predict the effects of sequence variation on protein function and biophysical parameters that are relevant for RNA and protein engineering and improvement.
• Utilize deep understanding of scientific literature and concepts to drive innovation for protein and RNA design.
• Actively and collaboratively promote scientific and technical innovation with other members of the team.

Qualifications:

• PhD degree in a relevant field (e.g. computer science, computational biology, bioengineering, or molecular biology) with 0-2 years of additional industry experience.
• Fluency with Python and data analysis using modern frameworks for deep learning (e.g. Pytorch, TensorFlow-Keras).
• Extensive experience parsing large datasets and applying machine learning to develop data-driven predictive and generative models within the context of iterative experimentation.
• Experience with macromolecular visualization and modeling tools such as PyMOL, AlphaFold2, Rosetta, and OpenMM.
• Track record of scientific publications demonstrating ability to implement deep learning models trained on limited datasets.
• Strong knowledge of the biological, chemical, and physical underpinnings of molecular biology, or intense curiosity about molecular design and eagerness to contribute to scientific and computational efforts.
• Familiarity using and maintaining cloud-based compute platforms such as AWS or Microsoft Azure.
• Excellent communication of complex scientific problems and ability to present strategies and scientific conclusions to a broad audience.