Researcher, Alignment Interpretability

Rebash

San Francisco (CA)

Presencial

USD 150 000 - 210 000

Tempo integral

Há 10 dias

Recebe uma resposta deste empregador

O teu currículo e carta de apresentação, adaptados exatamente ao que estão a contratar.

Ultrapassa os filtros ATS

Resumo da oferta

OpenAI is seeking a Researcher in Alignment Interpretability in San Francisco. You will develop and execute a research plan on mechanistic interpretability of deep networks, collaborating with a motivated team to advance safe AGI.

The role emphasizes publishing techniques, engineering scalable infrastructure to study model internals, and guiding research directions toward practical usefulness and long-term safety.

Qualificações

  • PhD in CS/ML or equivalent research experience.
  • Proven ability to design and publish AI safety research.
  • Experience with Python and reproducible workflows.

Responsabilidades

  • Develop and publish research on mechanistic interpretability.
  • Engineer infrastructure to study model internals at scale.
  • Collaborate across teams to pursue safety-aligned projects.
  • Guide research directions toward demonstrable usefulness.

Conhecimentos

Python
Quantitative reasoning
Research process
Collaboration

Formação académica

PhD in CS/ML
Research experience

Descrição da oferta de emprego

# Researcher, Alignment InterpretabilityOpenaionsitefull timeSan FranciscoApply## DescriptionAbout the Team The Interpretability team studies internal representations of deep learning models. We are interested in using representations to understand model behavior, and in engineering models to have more understandable representations. We are particularly interested in applying our understanding to ensure the alignment of powerful AI systems. Our working style is collaborative and curiosity-driven.About the Role OpenAI is seeking 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, in close collaboration with a highly motivated team. You will play a critical role in helping OpenAI ensure future models remain safe even as they grow in capability. This will make a significant impact on our goal of building and deploying safe AGI.In this role, you will:Develop and publish research on techniques for understanding representations of deep networks.Engineer infrastructure for studying model internals at scale.Collaborate across teams to work on projects that OpenAI is uniquely suited to pursue.Guide research directions toward demonstrable usefulness and/or long-term scalability.You might thrive in this role if you:Are excited about OpenAI’s mission of ensuring AGI benefits all of humanity, and are aligned with OpenAI’s charter .Show enthusiasm for long-term AI safety & alignment, and have thought deeply about technical paths to safe AGI.Bring experience in the field of AI safety & alignment, mechanistic interpretability, or spiritually related disciplines.Hold a Ph.D. or have research experience in computer science, machine learning, or a related field.Thrive in environments involving large-scale AI systems, and are excited to make use of OpenAI’s unique resources in this area.Possess 2+ years of research engineering experience and proficiency in Python or similar languages.Are deeply curious.
Obtém a tua avaliação gratuita e confidencial do currículo.

ou arrasta e larga o ficheiro aqui.

Similar jobs

Ofertas semelhantes que vale a pena comparar

Researcher, Alignment Interpretability
Researcher, Alignment Interpretability

OpenAI, Inc. • San Francisco (CA)

Presencial
USD 180 000 - 240 000
Researcher, Alignment Interpretability
Researcher, Alignment Interpretability

Society for AI Security • EUA

Presencial
USD 160 000 - 230 000
Mechanistic Interpretability Researcher
Mechanistic Interpretability Researcher

OpenAI, Inc. • San Francisco (CA)

Presencial
USD 180 000 - 240 000
Researcher, Alignment & Mechanistic Interpretability
Researcher, Alignment & Mechanistic Interpretability

Rebash • San Francisco (CA)

Presencial
USD 150 000 - 210 000
Researcher, Mechanistic Interpretability & Safe AI
Researcher, Mechanistic Interpretability & Safe AI

Society for AI Security • EUA

Presencial
USD 160 000 - 230 000
Researcher, Alignment
Researcher, Alignment

OpenAI, Inc. • San Francisco (CA)

Híbrido
GBP 90 000 - 120 000
Researcher, Alignment CoT Monitorability
Researcher, Alignment CoT Monitorability

Society for AI Security • San Francisco (CA)

Híbrido
USD 210 000 - 270 000
Relocation assistance
Hybrid work model (3 days in office)
Interpretability Researcher
Interpretability Researcher

Acceler8 • California

Presencial
USD 180 000 - 240 000
Researcher, Frontier Risk Mitigations
Researcher, Frontier Risk Mitigations

OpenAI, Inc. • San Francisco (CA)

Presencial
GBP 120 000 - 180 000
Researcher, Misalignment Monitoring Lead
Researcher, Misalignment Monitoring Lead

Applied Methods Ltd • San Francisco (CA)

Presencial
USD 38 000 - 50 000