Research Engineer / Scientist, Interpretability

at OpenAI

📍 San Francisco, United States

USD 310,000-460,000 per year

MIDDLE

✅ Hybrid

✅ Relocation

Used Tools & Technologies

Not specified

Required Skills & Competences
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

Python @ 5 Machine Learning @ 3 Hiring @ 3

Details

The Interpretability team studies internal representations of deep learning models. The team focuses on using representations to understand model behavior and engineering models to have more understandable representations, with applications to ensuring the safety of powerful AI systems. The working style is collaborative and curiosity-driven.

Responsibilities

Develop and publish research on techniques for understanding representations of deep networks.
Engineer infrastructure for studying model internals at scale.
Collaborate across teams on projects that leverage OpenAI's resources and capabilities.
Guide research directions toward demonstrable usefulness and/or long-term scalability.

Requirements

Strong background in engineering, quantitative reasoning, and the research process.
Experience in the field of AI safety, mechanistic interpretability, or related disciplines is valuable.
Hold a Ph.D. or have research experience in computer science, machine learning, or a related field (or equivalent experience).
2+ years of research engineering experience.
Proficiency in Python or similar languages.
Comfortable working with large-scale AI systems and studying model internals.
Deep curiosity and alignment with OpenAI's mission and safety-focused charter.

About OpenAI / Additional Information

OpenAI is an AI research and deployment company dedicated to ensuring general-purpose AI benefits all of humanity. The company emphasizes safety and inclusive perspectives. Background checks are administered in accordance with applicable law. OpenAI is an equal opportunity employer and provides reasonable accommodations to applicants with disabilities.

Benefits

Base salary range shown below; total compensation may include equity and performance-related bonuses.
Medical, dental, and vision insurance; employer contributions to Health Savings Accounts.
Pre-tax accounts (Health FSA, Dependent Care FSA, commuter expenses).
401(k) with employer match.
Paid parental, medical, caregiver leave; flexible PTO and paid holidays.
Mental health and wellness support.
Annual learning and development stipend.
Daily meals in offices and meal delivery credits as eligible.
Relocation support for eligible employees.
Additional taxable fringe benefits and more details provided during hiring process.