Tech Stack

Description

You will design, implement, train, and evaluate deep learning models for TCR–pMHC specificity prediction, integrating sequence and structural information. Working with a collaborative team, you will translate cutting-edge machine learning into diagnostic and therapeutic impact, leveraging large-scale proprietary immune receptor datasets.

Requirements

• PhD in a quantitative discipline + 5 years progressive experience applying machine learning to scientific or biological problems
• Progressive experience in development and deployment of deep learning methods
• Strong hands-on experience in Python and modern ML tooling (PyTorch preferred)
• Strong experience in deep learning architecture design and implementation
• Experience working with large datasets and high-performance computing environments
• Ability to independently define, scope, and execute complex technical research problems
• Strong written and verbal communication skills
• Demonstrated ability to collaborate effectively in cross-functional, multi-disciplinary teams
• Driven by impact: motivated to see models transition from research to clinical and commercial application

Responsibilities

• Design, implement, train, and iterate on novel deep learning models for TCR–pMHC specificity prediction.
• Extend and adapt advances in protein language models, structure prediction, generative modeling, and representation learning to the immune receptor setting.
• Utilize scalable training infrastructure to support large-scale model development and experimentation.
• Conduct rigorous benchmarking and evaluation strategies to ensure models are scientifically sound and practically superior.
• Translate biological principles of T cell recognition into principled modeling decisions.
• Influence large-scale experimental data generation to maximize modeling leverage and long-term performance gains.
• Provide input and technical recommendations to broader modeling discussions and roadmap planning.
• Work closely with computational biology, immunology, translational, and engineering teams to ensure models are robust, reproducible, and aligned with overall product goals.
• Communicate modeling insights, approaches, and results to cross-functional scientific audiences.
• Contribute to publications, presentations, etc. through technical execution and analysis.