Member of Technical Staff, Protein Design (AI)

Location: San Francisco, United States. Authorization to work in the U.S. is required; hirify.global participates in E-Verify.

Company

hirify.global is an AI research lab developing generative biological intelligence and scientific machine-learning systems for biology.

What you will do

• Develop machine-learning models for protein structure prediction, protein design, and structural biology.
• Train and fine-tune protein language models, geometric neural networks, diffusion models, and related architectures.
• Explore model architectures and learning objectives for protein sequence and structure.
• Build data pipelines, evaluation systems, and benchmarks that control for leakage, memorization, and contamination.
• Evaluate model accuracy, confidence, physical validity, generalization, and performance across diverse proteins and biological contexts.
• Run ablation studies, diagnose failure modes, improve training and inference efficiency, and collaborate across machine learning, computational biology, and engineering.

Requirements

• Must be authorized to work in the United States.
• Strong experience developing machine-learning models for protein structure prediction, structural biology, geometric deep learning, or a related area.
• Deep understanding of protein structure, structure-prediction and design methods, loss objectives, and modern architectures.
• Experience with biological datasets, data leakage and homology control, structural metrics, and rigorous evaluation.
• Fluency in Python and a modern deep-learning framework such as PyTorch or JAX.
• Experience with distributed training, accelerators, large datasets, reproducible experimentation, and cross-disciplinary collaboration.

Nice to have

• Contributions to protein structure-prediction systems, protein foundation models, geometric generative models, or structural-biology software.
• Experience with multiple sequence alignments, templates, coevolutionary methods, inverse folding, molecular simulation, or energy-based modeling.
• Experience modeling protein complexes, alternative conformational states, other macromolecules, small molecules, or molecular interactions.
• Experience with SE(3)- or E(3)-equivariant architectures, flow matching, uncertainty, confidence, or calibration.
• Publications, open-source contributions, or production systems demonstrating impact in generative modeling, molecular design, or scientific machine learning.

Culture & Benefits

• Hands-on research and engineering work at the intersection of machine learning, computational biology, and structural biology.
• Close collaboration with scientists and engineers to translate research advances into robust modeling capabilities.
• Mission focused on understanding biology, enabling cures, and developing responsible defenses against engineered biological threats.
• Equal employment opportunity and nondiscrimination across legally protected characteristics.