AI/ML Scientist, Protein Foundation Models

Responsibilities

• Advance foundation model training efforts including pretraining, fine-tuning, and evaluating folding, docking, language, and generative design models
• Bring depth in training methodology, architecture selection, and optimization
• Develop and scale training pipelines for distributed, multi-GPU and multi-node training runs
• Integrate foundation model outputs into mBER to improve binder design success rates
• Design and execute ML experiments with rigorous evaluation frameworks
• Establish best practices for mixed-precision training and computational efficiency at scale
• Produce clear documentation and analysis supporting architecture and training decisions

Requirements

• Demonstrated experience pretraining or fine-tuning protein foundation models
• Strong familiarity with AlphaFold architecture and training methodology
• 2+ years of hands-on experience with PyTorch and/or JAX
• Experience with large-scale model training (distributed, multi-GPU/multi-node)
• Solid understanding of deep learning architectures like transformers, attention, and diffusion
• Experience working with protein structure data (PDB, mmCIF) or sequence datasets
• Proficiency in Python scientific computing stack (NumPy, Pandas, scikit-learn)
• Strong statistical analysis and experimental design skills

Preferred Qualifications

• Experience with protein generative design methods (RFdiffusion, ProteinMPNN)
• Experience with protein language models (ESM family)
• Published research in computational biology or structural biology
• Familiarity with Ray, Kubernetes (EKS), and AWS
• Knowledge of protein engineering or wet lab techniques
• Previous biotech or pharma industry experience

About the Company

Manifold Bio is a platform biotechnology company pioneering AI-guided protein design and massively multiplexed in vivo screening to unlock tissue-targeted medicines and organism-scale models of living systems.