Researcher—Alignment & Mechanistic Interpretability

Triwill Group; San Francisco, Northern (CA, KY); Hybrid; USD 180,000 - 260,000; Full time

Job summary

OpenAI seeks a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, working closely with a motivated team.

You will help ensure future models remain safe as they grow in capability and have a meaningful impact on AI safety. This role emphasizes building scalable experiments, publishing results, and collaborating across

Qualifications

• Ph.D. or research experience in computer science, machine learning, or a related field.
• 2+ years of research engineering experience.
• Proficiency in Python or similar languages.

Responsibilities

• Develop and publish research on techniques for understanding representations of deep networks.
• Engineer infrastructure for studying model internals at scale.
• Collaborate across teams to pursue OpenAI-aligned projects.
• Guide research directions toward demonstrable usefulness and scalability.

Skills

Python

Research engineering

Quantitative reasoning

Collaborative culture

Education

Ph.D. or equivalent research experience

Tools

Python

Job description

OpenAI seeks a researcher passionate about understanding deep networks, with a strong background in engineering, quantitative reasoning, and the research process. You will develop and carry out a research plan in mechanistic interpretability, working closely with a motivated team.

You will help ensure future models remain safe as they grow in capability and have a meaningful impact on AI safety. This role emphasizes building scalable experiments, publishing results, and collaborating across