Remote
Senior or Principal Machine Learning Scientist
About this role
At Adaptive, we’re Powering the Age of Immune Medicine. Our goal is to harness the power of the adaptive immune system to transform the way diseases are diagnosed and treated. As an Adapter, you’ll have the opportunity to make a difference in people’s lives. With Adaptive, you’ll create a career highlight through collaboration with bright, curious colleagues working at the apex of innovation and application. It’s time for your next chapter.
Discover your story with Adaptive. Senior or Principal Machine Learning Scientist Position Overview Adaptive Biotechnologies is seeking a Senior or Principal Machine Learning Scientist to join a team developing deep learning models for TCR-pMHC specificity prediction. This role focuses on predicting interactions between T cell receptors and peptide-MHC complexes by integrating sequence, structural, and large-scale biological data.
In this role, you will work closely with computational scientists, immunologists, translational scientists, and machine learning engineers to build models that support Adaptive’s diagnostic and therapeutic initiatives. The work draws on a large and growing proprietary immune receptor dataset purpose-built for this machine learning problem, as well as shared GPU infrastructure and a close feedback loop between model development and experimental data generation.
At the Senior level, the role emphasizes independent ownership of major modeling workstreams, rigorous technical execution, and strong cross-functional collaboration. At the Principal level, the role expands to broader technical leadership, modeling and data strategy, roadmap influence, and long-term direction setting across teams. Key Responsibilities and Essential Functions Design, implement, train, and evaluate deep learning models for TCR-pMHC specificity prediction.
Integrate sequence, structural, and large-scale biological data into principled modeling approaches. Adapt advances in protein structure prediction, protein-protein interaction modeling, protein language models, representation learning, and related areas to immune receptor prediction. Develop rigorous benchmarking and evaluation strategies to assess model performance, generalization, and practical utility. Translate biological principles of T cell recognition into modeling decisions.