PhD Candidate in AI-Driven Protein Design (Biotechnology, Remote)

Job summary

This position is for a computationally focused PhD candidate working on AI-driven design of protein minibinders for T cell immunotherapy. The project aims to develop algorithms and modeling infrastructure to create highly specific minibinders that target peptide-MHC complexes, addressing challenges in specificity and cross-reactivity.

Qualifications

• A strong background in deep learning or generative modeling, with relevant project or research experience.
• Proficiency in Python and familiarity with at least one deep learning framework (e.g., PyTorch, JAX).
• Excellent analytical skills and ability to tackle open-ended research problems.
• Strong communication skills and a collaborative approach to interdisciplinary work.

Responsibilities

• Design and generate structurally diverse minibinder libraries using diffusion-based models and protein language models.
• Develop filtering pipelines to identify high-confidence binder candidates from large in silico libraries.
• Build active learning strategies to optimize experimental validation of candidates.
• Develop computational models for cross-reactivity screening across diverse pMHC sequences.
• Integrate experimental data into model training and refinement loops.
• Explore new protein design paradigms as the field evolves.
• Publish findings in peer-reviewed journals and present at conferences.
• Contribute to teaching and mentoring within the lab.

Skills

• Hands-on experience with generative protein design tools and models.
• Familiarity with protein structure and bioinformatics.
• Knowledge of immunology or antigen presentation concepts.
• Experience with high-performance or GPU-accelerated computing workflows.

Education

• A two-year master's degree (120 ECTS points) or equivalent academic level is required.