Astera · San Francisco
OtherScienceFullTimeposted 2mo ago
Astera is a private foundation on a mission to steer science and technology toward an abundant future. We believe the coming years will bring an era of unprecedented scientific and technological advancement as exponential progress in AI converges with central advances in other fields to dramatically accelerate innovation. This inflection point provides an unparalleled opportunity to fundamentally rethink the institutions, systems, and tools that drive scientific progress.
Unlike traditional non-profit research organizations, projects supported by Astera operate like high-velocity startups, allowing us to focus on ambitious goals, match structure to problem, and attract strong technical talent and leadership. You can read more about our mission, vision, and programming here.
Prism is a program within Radial, the basic life sciences division of the Astera Institute. We are making protein motion measurable, predictable, and actionable by building open infrastructure for studying protein dynamics directly from experimental data. Function emerges from the ensemble of conformations a protein adopts and how it moves between them, and we are rebuilding the structural biology stack around that premise: data collection, modeling, representation, and interpretation. We work at the interface of experimental structural biology (crystallography, cryo-EM), machine learning, computational biophysics, and open scientific tooling. Our team spans computational biologists, ML researchers, software engineers, and program staff, collaborating across Radial, Astera, and partner institutions.
Build ensemble-aware protein representations that integrate PLM and LLM embeddings with experimentally derived structural heterogeneity for functional prediction
Design, develop, and maintain large-scale bioinformatic pipelines capable of processing and managing complex, high-dimensional datasets
Fine-tune or architect ML models to capture sequence-structure-function relationships, with a focus on dynamic and conformational features
Synthesize diverse data sources spanning evolutionary history, binding affinity, allostery, and functional annotations to improve model performance and biological relevance
Collaborate closely with experimental partners to ground computational representations in real biological measurements and ensure models are continuously refined against experimental ground truth
Contribute to the broader Prism infrastructure, helping establish community-wide standards and tools for dynamic structural biology
PhD in bioinformatics, computational biology, machine learning, or a related field.
Strong understanding of protein structure and function.
Demonstrated experience building large bioinformatic pipelines and managing high-dimensional datasets.
Proficiency in fine-tuning or modifying ML models (e.g., transformer-based architectures).
Familiarity with protein language models (ESM, AlphaFold, etc.) is a plus.
Collaborative, team-oriented mindset with the ability to drive research questions from conception to execution.
Commensurate with experience.