Member of Technical Staff, Post-Training
Hybrid (SF Bay Area or Tokyo, Japan)Full-timePosted 7mo ago
About the role
Role focused on developing post-training methods, data, and infrastructure to turn pretrained biology-focused models into useful, steerable, robust systems. Bridges fundamental research and practical engineering, emphasizing long-context reasoning, objective design, and interaction with downstream workflows.
Responsibilities
- Develop and tune post-training recipes. Design and iterate on post-training stages, datasets, reward signals, and hyperparameters for biological world models. Study how data mixtures, objective design, curriculum, and training schedules affect model behavior.
- Build evaluations that actually matter. Collaborate with the science team to develop and refine evaluation suites for biological reasoning, scientific usefulness, long-context behavior, robustness, and model reliability.
- Debug model behavior end-to-end. Investigate failure modes in training runs and model outputs, distinguish signal from noise, trace problems to data, optimization, evaluation design, or systems issues.
- Work on preference- and feedback-driven learning. Explore methods such as preference modeling, reward modeling, synthetic feedback, or related post-training approaches.
- Improve data for post-training. Define, curate, or generate high-quality post-training datasets, including expert-informed data, synthetic data, and task-specific examples grounded in biological workflows.
- Study scaling in post-training. Measure how performance changes with dataset size, recipe complexity, compute budget, and model family.
- Collaborate across research and engineering. Work with training systems, architecture, and biology-facing research teams to ground methods in large-scale experimentation and downstream scientific use.
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, with 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, especially the ability to explain technical findings clearly across research, engineering, and scientific collaborators.
- Curiosity, rigor, and a bias toward iteration: you like improving systems by repeatedly tightening the loop between hypotheses, experiments, and insight.
Skills
Required:Post-training method designEvaluation framework designExperiment design and analysisPythonPyTorch
Benefits
- Competitive compensation
- comprehensive benefits
- support for continual learning
Last updated May 28, 2026. Interested? Apply on the company site.
About Radical Numerics
Next-gen AI lab for recursive self-improvement
Radical Numerics - Next-gen AI lab for recursive self-improvement
AIAI labrecursive self-improvement
More open roles at Radical Numerics
- Product Manager5mo agoHybrid (San Francisco, CA)
- Senior Engineering Manager5mo agoHybrid (SF Bay Area or Tokyo, Japan)
- Member of Technical Staff, Statistical Genetics5mo agoHybrid (SF Bay Area)
- Chief of Staff5mo agoHybrid (San Francisco Bay Area)
- Member of Technical Staff, Backend Engineering7mo agoHybrid (SF Bay Area), Hybrid (Tokyo, JP) · Engineering