Research Engineer
IrregularAI Security company
Tel Aviv, IsraelMid
Sequoia Capital
Redpoint Ventures
Swish Ventures
Assaf Rappaport
Ofir Ehrlich
Dell Technologies Capital
Data & AI
About the role
TL;DR
Evaluate and secure frontier AI models at Irregular.
- •As a research engineer at Irregular, you'll be at the forefront of building systems to evaluate and secure frontier AI models.
- •You'll work on infrastructure and experiments to assess model capabilities, implement agent frameworks, and develop mitigations for advanced AI systems.
- •Key Responsibilities Building a tool to continuously evaluate models and mitigate their risks.
- •Designing and building challenges that measure a model's ability to evade discovery.
- •Developing controlled environment frameworks for more secure use of frontier models.
- •Requirements Strong production programming skills.
- •Strong problem-solving and analytical skills.
- •Interest in AI and cybersecurity.
Required skills
PythonNLPLLMsKubeflowCI/CDDockerKubernetesGitLinux
Nice-to-have skills
TensorFlowPyTorchscikit-learn
Domain expertise
cybersecurity
Tech stack
PythonTensorFlowPyTorchscikit-learnNLPLLMsKubeflowCI/CDDockerKubernetesGitLinux
