Researcher, Chain-of-Thought Monitorability & Alignment

OpenAI; San Francisco (CA); Hybrid; USD 120,000 - 150,000; Full time

Benefits offered by this job

Relocation assistance

Hybrid work model

Job summary

OpenAI in San Francisco is looking for a researcher with strong empirical ML expertise to investigate model behavior and monitorability. You will design experiments and translate findings into practical recommendations.

The ideal candidate will have experience training large ML models and a passion for AI safety and alignment. This position offers a hybrid work model and relocation assistance for new employees.

Qualifications

• Strong hands-on experience training, evaluating, or debugging large ML models.
• Deep curiosity and interest in alignment and model behavior.

Responsibilities

• Design and run empirical studies of chain-of-thought monitorability.
• Build evaluations to measure monitorability and model behavior.

Skills

Empirical ML expertise

Alignment research

Model interpretability

Education

Relevant degree in machine learning or related field

Tools

Python

TensorFlow

PyTorch

Job description

OpenAI in San Francisco is looking for a researcher with strong empirical ML expertise to investigate model behavior and monitorability. You will design experiments and translate findings into practical recommendations.

The ideal candidate will have experience training large ML models and a passion for AI safety and alignment. This position offers a hybrid work model and relocation assistance for new employees.