OpenAI

3 months ago

Researcher, Alignment Science

✓ 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

Design and run experiments to help increasingly capable models follow user intent, stay calibrated on correctness and risk, and honestly surface their mistakes. Conduct hands-on training, evaluation design, and research infrastructure to translate alignment research into frontier model development, with collaboration across RL, evaluations, safety, and product teams.

Location: San Francisco

Workplace: Hybrid

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Key Responsibilities

•Design and implement alignment experiments focused on intent following, honesty, calibration, and robustness.
•Train and evaluate models using reinforcement learning and other empirical ML methods.
•Develop evaluations for failure modes such as hallucination, instruction-following failures, reward hacking, covert actions, and scheming.
•Study methods that encourage models to verify their behavior and report shortcomings honestly, including confession-style training objectives.
•Build monitoring and inference-time interventions to ensure compliant behavior or surface model issues to users or downstream systems.

Pay and Benefits

Salary: USD 250,000 - 445,000 annually

Equity and Bonus:Equity

Perks:EquityRelocation

Key Requirements

•Hands-on experience training, evaluating, or debugging large ML models, especially LLMs.
•Excellent engineering skills in Python and modern ML frameworks such as PyTorch.
•Strong mathematical rigor and ability to turn ambiguous research questions into measurable experiments.
•Experience with reinforcement learning, post-training optimization, scalable oversight, or related empirical ML research.
•Ability to operate independently with minimal day-to-day handholding.

Skills:CommunicationProblem-solvingCollaborationAdaptabilityAttention to detail

Languages:English

Tech Stack:PythonPyTorchReinforcement Learning

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, Alignment Science

✓ 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: Hybrid

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Key Responsibilities

•Design and implement alignment experiments focused on intent following, honesty, calibration, and robustness.
•Train and evaluate models using reinforcement learning and other empirical ML methods.
•Develop evaluations for failure modes such as hallucination, instruction-following failures, reward hacking, covert actions, and scheming.
•Study methods that encourage models to verify their behavior and report shortcomings honestly, including confession-style training objectives.
•Build monitoring and inference-time interventions to ensure compliant behavior or surface model issues to users or downstream systems.

Pay and Benefits

Salary: USD 250,000 - 445,000 annually

Equity and Bonus:Equity

Perks:EquityRelocation

Key Requirements

•Hands-on experience training, evaluating, or debugging large ML models, especially LLMs.
•Excellent engineering skills in Python and modern ML frameworks such as PyTorch.
•Strong mathematical rigor and ability to turn ambiguous research questions into measurable experiments.
•Experience with reinforcement learning, post-training optimization, scalable oversight, or related empirical ML research.
•Ability to operate independently with minimal day-to-day handholding.

Skills:CommunicationProblem-solvingCollaborationAdaptabilityAttention to detail

Languages:English

Tech Stack:PythonPyTorchReinforcement Learning

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