OpenAI8 дней назад

Researcher, Frontier Cybersecurity Risks

Зарплата не указана

РЫНОК

65 900 ₽медиана по профессии

AI Researcher · 12 вакансий с указанной зарплатой

13 833половина предложений: 24 084–65 900143 300

Работодатель не указал зарплату — сравните с рынком сами.

Полная занятостьSan Francisco

Обязанности

01Measurement: monitoring and predicting the evolving capabilities of frontier AI systems
02Mitigation: keeping misuse safeguards, alignment tools, and security measures on track to adequately address extreme threats that might arise in the future
03Coordination: setting mitigation targets by maintaining OpenAI’s preparedness framework, and partnering with other staff to achieve these targets
04Design and implement mitigation components for model-enabled cybersecurity misuse—spanning prevention, monitoring, detection, and enforcement—under the guidance of senior technical and risk leadership
05Integrate safeguards across product surfaces in partnership with product and engineering teams, helping ensure protections are consistent, low-latency, and scale with usage and new model capabilities
06Evaluate technical trade-offs within the cybersecurity risk domain (coverage, latency, model utility, and user privacy) and propose pragmatic, testable solutions
07Collaborate closely with risk and threat modeling partners to align mitigation design with anticipated attacker behaviors and high-impact misuse scenarios
08Execute rigorous testing and red-teaming workflows, helping stress-test the mitigation stack against evolving threats (e.g., novel exploits, tool-use chains, automated attack workflows) and across different product surfaces—then iterate based on findings

01Have a passion for AI safety and are motivated to make cutting-edge AI models safer for real-world use
02Bring demonstrated experience in deep learning and transformer models
03Are proficient with frameworks such as PyTorch or TensorFlow
04Possess a strong foundation in data structures, algorithms, and software engineering principles
05Are familiar with methods for training and fine-tuning large language models, including distillation, supervised fine-tuning, and policy optimization
06Excel at working collaboratively with cross-functional teams across research, security, policy, product, and engineering
07Have significant experience designing and deploying technical safeguards for abuse prevention, detection, and enforcement at scale
08(Nice to have) Bring background knowledge in cybersecurity or adjacent fields

01OpenAI is an equal opportunity employer and does not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other protected characteristics
02Background checks are administered in accordance with applicable law; qualified applicants with arrest or conviction records are considered consistent with those laws
03Reasonable accommodations are provided to applicants with disabilities upon request