Member of Technical Staff, Post-Training at radical-numerics

Department: R&D

Setup: On-site
Location: San Francisco, California
Level: senior
Posted: Mar 17, 2026

Description

Radical Numerics is hiring a Member of Technical Staff, Post-Training to develop and tune post-training methods for biological world models. The role focuses on post-training recipes, datasets, reward and feedback signals, evaluation suites, debugging model behavior, scaling studies, and collaboration across research and engineering. Candidates should have a strong track record in machine learning research or engineering, especially frontier-model training, post-training, alignment, evaluation, or data quality, along with Python and PyTorch proficiency and strong experimental rigor.

Required Skills

Python
PyTorch
Post-training
Evaluation
Preference modeling
Synthetic data
Debugging

Additional Information

Required Previous Experiences: Strong track record in machine learning research or engineering, especially frontier-model training, post-training, alignment, evaluation, or data quality.
Proficiency in building production-quality software and research infrastructure, ideally in Python and PyTorch, with comfort debugging large-scale training workflows.
Preferred Qualifications: 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 machine learning systems, model tooling, or research infrastructure.