Frontier AI Evaluation Architect

United States Digital Space LLC; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

United States Digital Space LLC is seeking a researcher focused on building environments for frontier evaluations that drive progress towards safe AGI/ASI. You will guide ambitious training runs with prominent industry impact.

The ideal candidate has a strong foundation in machine learning and experience with modern methods. Join us to help shape the future of artificial intelligence development and deployment.

Qualifications

• Strong technical fundamentals in machine learning, software engineering, and related fields.
• Hands-on experience with LLMs, RL and related methodologies.
• Ability to navigate vague problems to define concrete experiments.

Responsibilities

• Create ambitious RL environments for model evaluation.
• Develop methodologies for exploring model behavior.
• Steer training for major runs and evaluate outcomes.

Skills

Machine learning

Software engineering

Systems

Statistics

RLHF/RLAIF

Model training

Education

Degree in relevant field

Tools

LLMs

Synthetic data

Job description

United States Digital Space LLC is seeking a researcher focused on building environments for frontier evaluations that drive progress towards safe AGI/ASI. You will guide ambitious training runs with prominent industry impact.

The ideal candidate has a strong foundation in machine learning and experience with modern methods. Join us to help shape the future of artificial intelligence development and deployment.