Member of Technical Staff, Post-Training

The role

You will develop training and evaluation loops that shape biological world models after pretraining. You will work on methods, data, and infrastructure to improve model behavior on scientific tasks.

What you will do

• Develop and tune post-training recipes.
• Design and iterate on post-training stages, datasets, reward signals, and hyperparameters.
• Build evaluations for biological reasoning, scientific usefulness, long-context behavior, robustness, and model reliability.
• Debug model behavior end-to-end.
• Work on preference- and feedback-driven learning.
• Improve data for post-training.
• Study scaling in post-training.
• Collaborate across research and engineering.

Required qualifications

• Strong track record in ML research or engineering, especially in frontier-model training, post-training, alignment, evaluation, data quality, or related areas.
• Proficiency in building production-quality software and research infrastructure, ideally in Python and PyTorch.
• Comfort debugging large-scale training workflows.
• Ability to design careful experiments, interpret ambiguous results, and separate real effects from artifacts, bugs, or benchmark overfitting.
• Excellent written and verbal communication skills.
• Curiosity, rigor, and a bias toward iteration.

Nice to have

• Experience with RLHF, RLAIF, preference optimization, reward modeling, rejection sampling, or other post-training methods for large models.
• Experience designing or operating evaluation frameworks for model quality, reliability, safety, or scientific task performance.
• Familiarity with synthetic data generation, annotation workflows, or expert-in-the-loop data collection.
• Background in applied math, systems, computational biology, or another quantitative scientific field.
• Contributions to open-source ML systems, model tooling, or research infrastructure.

Benefits

• Competitive compensation
• Comprehensive benefits
• Support for continual learning

Before you apply

• Radical Numerics participates in E-Verify to confirm authorization to work in the U.S.

About the company

Radical Numerics is an AI research lab building general biological intelligence. Their mission is to master the code of life and reduce human suffering.