Member of Technical Staff, Protein Design at radical-numerics

Department: R&D

Location: San Francisco, California
Level: senior
Posted: Jul 22, 2026

Description

Radical Numerics is hiring a Member of Technical Staff, Protein Design, to develop machine-learning systems for protein structure prediction, design, and structural biology. The role involves training and fine-tuning protein language models, geometric neural networks, diffusion models, and other scientific architectures; building data pipelines and evaluation systems; designing benchmarks; analyzing model performance; running ablation studies; and improving training and inference on large-scale compute systems. The position requires strong experience in protein modeling, structural biology, geometric deep learning, and scientific machine learning, along with Python and a modern deep-learning framework.

Required Skills

Machine learning
Protein prediction
Geometric deep learning
Diffusion models
Python
PyTorch
JAX
Distributed training

Additional Information

Required Previous Experiences: Experience developing machine-learning models for protein structure prediction, structural biology, or geometric deep learning
Experience training or fine-tuning protein language models, structure models, diffusion models, or large scientific machine-learning systems
Experience building and validating biological datasets while controlling for data leakage, homology, and benchmark contamination
Experience with distributed training, accelerators, large datasets, and reproducible experimentation
Preferred Qualifications: Contributions to protein structure-prediction systems, protein foundation models, geometric generative models, or widely used structural biology software
Familiarity with multiple sequence alignments, templates, coevolutionary methods, inverse folding, molecular simulation, or energy-based modeling
Experience modeling other macromolecules, small molecule systems, and molecular interactions
Understanding of major protein structure datasets, benchmarks, or community evaluation efforts
Experience modeling protein complexes or alternative conformational states
Experience with SE(3)- or E(3)-equivariant architectures, diffusion models, flow matching, or generative modeling of molecular coordinates
Experience evaluating model confidence, uncertainty, and calibration
Familiarity with experimental methods for determining protein structure
A record of publications, open-source contributions, or production systems demonstrating impact in generative modeling, molecular design, or scientific machine learning