Frontier AI Safety Researcher & Evaluations

Society for AI Security; San Francisco (CA); Hybride; USD 140 000 - 190 000; Plein temps

Avantages offerts par ce poste

Relocation assistance

Hybrid work model

Résumé du poste

OpenAI is seeking a Researcher, Agent Safety, Training and Evaluations to help reduce the risk of unsafe agent actions while preserving autonomy. The role focuses on training frontier models, building scalable evaluation systems, and collaborating with cross-functional partners to deploy mitigations in large-scale training environments.

Based in San Francisco with a hybrid work model, the role emphasizes rigorous experimentation, safety-focused research, and practical impact on real-world AI

Qualifications

• Have demonstrated strength in research engineering, ML engineering, quantitative research, or applied model research, with the ability to own ambiguous projects end to end.
• Bring excellent technical execution across experimentation, data, evaluation, and/or infrastructure, plus strong intuition for modern frontier-model research.
• Are motivated by agent safety and eager to work on urgent, practical problems even if your prior work was outside safety or alignment.

Responsabilités

• Train and evaluate frontier models to reduce harmful or misaligned agent actions, forming clear hypotheses and executing independently through ambiguity.
• Mine incidents and build scalable measurement, data-processing, and evaluation systems that turn real failures into repeatable safety signals.
• Collaborate closely with post-training, capabilities, oversight, and pre-training partners to ship research-backed mitigations into large-scale training and agent systems.

Connaissances

Research engineering

ML engineering

Quantitative research

Applied model research

Description du poste

OpenAI is seeking a Researcher, Agent Safety, Training and Evaluations to help reduce the risk of unsafe agent actions while preserving autonomy. The role focuses on training frontier models, building scalable evaluation systems, and collaborating with cross-functional partners to deploy mitigations in large-scale training environments.

Based in San Francisco with a hybrid work model, the role emphasizes rigorous experimentation, safety-focused research, and practical impact on real-world AI