Post-Training Engineer

About the role

The work combines research experiments with reliable fine-tuning, evaluation, measurement, and debugging tools.

What you'll do

• Implement and compare post-training methods with clear evaluation criteria.
• Develop reliable pipelines for model fine-tuning and evaluation.
• Create tools that measure model quality across relevant dimensions.
• Debug training problems and unexpected model behavior with researchers and engineers.

What we're looking for

• Strong software engineering skills and experience developing complex machine learning systems.
• Experience training, fine-tuning, or evaluating language models.
• Experience balancing open-ended research with reproducible engineering work.
• The ability to debug difficult, time-sensitive problems while priorities change.

Preferred experience

• Experience with reinforcement learning or preference optimization for language models.

Equal opportunity

Entlegnant, the company behind Leiolai, is an equal opportunity employer. We consider qualified applicants without regard to race, color, religion, sex, gender identity or expression, sexual orientation, national origin, ancestry, age, disability, veteran status, genetic information, or any other status protected by law.

Applicants must be at least 18. If you need an accommodation during the application process, email talent@leiolai.com.