2 months ago
Base Salary
$295k - $445k/yr
Responsibilities
- Design and implement mitigation components for cybersecurity misuse.
- Integrate safeguards across product surfaces in collaboration with product and engineering teams.
- Evaluate technical trade-offs and propose pragmatic solutions.
- Collaborate with risk and threat modeling partners to align mitigation design with anticipated threats.
- Execute testing and red-teaming workflows to stress-test the mitigation stack.
Requirements
- Passion for AI safety and motivation to enhance AI model security.
- Demonstrated experience in deep learning and transformer models.
- Proficiency with frameworks such as PyTorch or TensorFlow.
- Strong foundation in data structures, algorithms, and software engineering principles.
- Familiarity with training methods for large language models.
- Experience designing and deploying technical safeguards for abuse prevention.
- Background knowledge in cybersecurity is a plus.
Tech Stack
PyTorchTensorFlow
Categories
About OpenAI
OpenAI builds and deploys large-scale AI models and tools—including ChatGPT, GPT-4–class models, DALL·E, and Whisper—sold via APIs and enterprise subscriptions to developers and businesses. It monetizes through usage-based API pricing and ChatGPT Plus/Team/Enterprise, and also reaches customers via Microsoft’s Azure OpenAI Service. Founded in 2015 and headquartered in San Francisco, it operates as a private partnership.