OpenAI

3 months ago

Researcher, Misalignment Research

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 2 hours agoStatus: Live

Job Summary

Senior researcher role focused on red-teaming and AI safety within OpenAI's Safety Systems. You will design and run adversarial demonstrations, build evaluations, and develop automated tooling to stress-test alignment, contributing to safer product releases and long-term safety strategy.

Location: San Francisco

Workplace: Onsite

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Seniority: Manager level

Key Responsibilities

•Design and implement worst-case demonstrations that reveal AGI alignment risks to stakeholders.
•Develop adversarial and system-level evaluations grounded in demonstrations, driving adoption across OpenAI.
•Create automated tools and infrastructure to scale automated red-teaming and stress testing.
•Conduct research on failure modes of alignment techniques and propose improvements.
•Mentor engineers and researchers, fostering a culture of rigorous, impact-oriented safety work.

Pay and Benefits

Salary: USD 295,000 - 445,000 annually

Equity and Bonus:Equity

Perks:Equity

Key Requirements

•4+ years of experience in AI red-teaming, security research, adversarial ML, or related safety fields.

Experience:4+ yearsAI safetyMisalignmentAdversarial ML

Skills:Problem-solvingCommunicationCollaborationResearchAnalytical thinking

Languages:English

Tech Stack:MLMachine learningEvaluation infrastructureLarge-scale codebases

Company Brief

OpenAI

Develops and deploys advanced generative AI models (including ChatGPT and DALL·E) and AI infrastructure, providing APIs and consumer products to accelerate safe AGI for broad benefit.

Industry: AI & Machine Learning

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Scaleup

Valuation: Hectocorn (USD 100B+)

Funding: Series E+

Headquarters: San Francisco, United States

Founded: 2015

Glassdoor: 4.4

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

OpenAI

3 months ago

Researcher, Misalignment Research

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 2 hours agoStatus: Live

Job Summary

Location: San Francisco

Workplace: Onsite

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Seniority: Manager level

Key Responsibilities

•Design and implement worst-case demonstrations that reveal AGI alignment risks to stakeholders.
•Develop adversarial and system-level evaluations grounded in demonstrations, driving adoption across OpenAI.
•Create automated tools and infrastructure to scale automated red-teaming and stress testing.
•Conduct research on failure modes of alignment techniques and propose improvements.
•Mentor engineers and researchers, fostering a culture of rigorous, impact-oriented safety work.

Pay and Benefits

Salary: USD 295,000 - 445,000 annually

Equity and Bonus:Equity

Perks:Equity

Key Requirements

•4+ years of experience in AI red-teaming, security research, adversarial ML, or related safety fields.

Experience:4+ yearsAI safetyMisalignmentAdversarial ML

Skills:Problem-solvingCommunicationCollaborationResearchAnalytical thinking

Languages:English

Tech Stack:MLMachine learningEvaluation infrastructureLarge-scale codebases

Company Brief

OpenAI

Develops and deploys advanced generative AI models (including ChatGPT and DALL·E) and AI infrastructure, providing APIs and consumer products to accelerate safe AGI for broad benefit.

Industry: AI & Machine Learning

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Scaleup

Valuation: Hectocorn (USD 100B+)

Funding: Series E+

Headquarters: San Francisco, United States

Founded: 2015

Glassdoor: 4.4

Website LinkedIn Glassdoor