Research Engineer: AI Safety & Alignment

Anthropic; San Francisco (CA); Hybrid; USD 350,000 - 500,000; Full time

Benefits offered by this job

Competitive compensation

Generous vacation and parental leave

Flexible working hours

Job summary

Anthropic is seeking a Research Engineer on Alignment Science to contribute to AI safety research based in San Francisco. The role involves developing techniques for scalable oversight and creating methods for AI control, with a focus on responsible scaling.

The ideal candidate will have significant experience in software engineering or research, along with a passion for AI's ethical implications.

Competitive salary and generous benefits offered.

Qualifications

• Have significant software or research engineering experience.
• Familiarity with technical AI safety research is advantageous.
• Experience contributing to empirical AI research projects.

Responsibilities

• Build and run thorough machine learning experiments.
• Develop techniques to ensure AI systems remain safe and harmless.
• Conduct exploratory research on AI safety and alignment.

Skills

Software engineering experience

Machine learning knowledge

Technical AI safety research

Research engineering experience

Collaboration skills

Education

Bachelor's degree or equivalent

Tools

Python

Kubernetes

Job description

Anthropic is seeking a Research Engineer on Alignment Science to contribute to AI safety research based in San Francisco. The role involves developing techniques for scalable oversight and creating methods for AI control, with a focus on responsible scaling.

The ideal candidate will have significant experience in software engineering or research, along with a passion for AI's ethical implications.

Competitive salary and generous benefits offered.