Post-Training Researcher (AI)

TL;DR

Post-Training Researcher (AI): Designing and executing data collection strategies for post-training by combining human feedback and synthetic data to guide model behavior. Focus on developing scalable frameworks, evaluating metrics, and publishing research to advance human-centered AI systems.

Location: San Francisco, California

Compensation: $350,000 - $475,000 USD

Company

hirify.global empowers humanity through advancing collaborative general intelligence, creating widely used AI products.

What you will do

• Design and execute data collection and synthesis strategies for post-training.
• Develop pipelines for scalable human labeling and synthetic data generation.
• Research human preferences to improve model reasoning and helpfulness.
• Iterate on evaluations to ensure meaningful metrics.
• Publish and present research to share insights with the community.

Requirements

• Strong engineering skills and experience with data curation.
• Proficiency in Python and familiarity with deep learning frameworks.
• Ability to design and interpret experiments with scientific rigor.
• Bachelor’s degree in a related discipline.