Machine Learning Scientist/Sr Scientist - Antibody Property Prediction & Generative Design

Role Summary

The Machine Learning Scientist/Sr Scientist, Antibody Property Prediction & Generative Design plays a critical role within the TuneLab platform, focusing on antibody and biologic drug development. This role combines deep expertise in antibody engineering, protein design, and immunology with advanced machine learning for sequence modeling and structure prediction to accelerate antibody discovery, optimization, and developability assessment across a federated network.

Responsibilities

• Antibody Property Prediction: Build multi-task learning frameworks for antibody properties such as binding affinity, specificity, stability, immunogenicity, and developability metrics from sequence and structural features.
• Antibody Sequence Generation: Develop generative models (transformers, diffusion models, evolutionary models) for antibody design, including CDR optimization, humanization, and affinity maturation while maintaining structural integrity.
• Structure-Aware Design: Integrate structural modeling and prediction (AlphaFold, ESMFold) with generative approaches to ensure proper folding, CDR loop conformations, and epitope recognition.
• Developability Optimization: Create models that optimize multiple developability criteria (expression yield, solubility, viscosity, post-translational modifications) for manufacturing and formulation.
• Species Cross-Reactivity: Design antibodies with desired species cross-reactivity profiles for preclinical development, leveraging cross-species binding data.
• Antibody-Antigen Modeling: Build models for predicting antibody-antigen interactions, epitope mapping, and paratope design using sequence and structural information.

Qualifications

• PhD in Computational Biology, Protein Engineering, Immunology, Biochemistry, or a related field from an accredited institution.
• Minimum of 2 years of experience in antibody or protein therapeutic development within the biopharmaceutical industry.
• Strong experience with protein sequence analysis and structural biology.
• Proven track record in machine learning applications to biological sequences.
• Deep understanding of antibody structure-function relationships and immunology.

Additional Requirements

• Up to 10% travel to attend key industry conferences; relocation is provided.
• Experience with immune repertoire sequencing and analysis preferred.
• Publications on antibody design, protein engineering, or therapeutic development preferred.
• Expertise in protein language models and transformer architectures preferred.
• Knowledge of antibody manufacturing and CMC considerations preferred.
• Experience with display technologies (phage, yeast, mammalian) preferred.
• Understanding of clinical immunogenicity and prediction methods preferred.
• Proficiency in protein modeling tools (Rosetta, MOE, Schrödinger BioLuminate) preferred.
• Familiarity with antibody-drug conjugates and bispecific platforms preferred.
• Experience with federated learning in biological applications preferred.
• Portfolio mindset balancing innovation with practical developability.