Frontier AI Cybersecurity Risks Researcher

Applied Methods Ltd; San Francisco (CA); On-site; USD 30,000 - 45,000; Full time

Job summary

OpenAI is seeking a Researcher for Frontier Cybersecurity Risks to design and implement an end-to-end mitigation stack that reduces severe cyber misuse across OpenAI products. The role requires deep technical expertise in deep learning, transformer models, and safeguarding systems, with close collaboration across research, security, policy, product, and engineering teams.

You will evaluate trade-offs in coverage, latency, model utility, and user privacy while advancing protections that adapt as

Qualifications

• Experience in deep learning and transformer models.
• Proficient with PyTorch or TensorFlow.
• Strong foundations in data structures, algorithms, and software engineering principles.
• Familiar with training and fine-tuning large language models, including distillation, supervised fine-tuning, and policy optimization.
• Excel at working collaboratively with cross-functional teams across research, security, policy, product, and engineering.
• Experience designing and deploying technical safeguards for abuse prevention, detection, and enforcement at scale.

Responsibilities

• Design and implement mitigation components for model-enabled cybersecurity misuse—spanning prevention, monitoring, detection, and enforcement.
• Integrate 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.
• Evaluate technical trade-offs within the cybersecurity risk domain and propose pragmatic, testable solutions.
• Collaborate closely with risk and threat modeling partners to align mitigation design with attacker behaviors and high-impact misuse scenarios.
• Execute rigorous testing and red-teaming workflows, stress-testing the mitigation stack against evolving threats across product surfaces, then iterate.

Skills

deep learning

transformer models

PyTorch

TensorFlow

data structures

algorithms

software engineering

LLM training

distillation

supervised fine-tuning

policy optimization

cross-functional collaboration

cybersecurity knowledge

Tools

PyTorch

TensorFlow

Job description

OpenAI is seeking a Researcher for Frontier Cybersecurity Risks to design and implement an end-to-end mitigation stack that reduces severe cyber misuse across OpenAI products. The role requires deep technical expertise in deep learning, transformer models, and safeguarding systems, with close collaboration across research, security, policy, product, and engineering teams.

You will evaluate trade-offs in coverage, latency, model utility, and user privacy while advancing protections that adapt as