← All Positions
AI Security Researcher
About the Role
As an AI Security Researcher, you will identify and mitigate vulnerabilities in Large Language Models. You will research novel attack vectors, develop defense mechanisms, and contribute to the core security capabilities of Promptention Guard.
What You'll Do
- Research and identifying novel LLM vulnerabilities (prompt injection, jailbreaks)
- Develop detection and mitigation techniques for AI-specific threats
- Design and execute red-teaming methodologies for generative AI models
- Publications and contributions to the AI security research community
- Collaboration with engineering teams to productionize defense research
Requirements
- PhD or Master's degree in Computer Science, Machine Learning, or relevant field
- Strong publication record or demonstrated research in AI/ML security
- Deep understanding of Transformer architectures and LLM internals
- Proficiency in Python and deep learning frameworks (PyTorch/TensorFlow)
- Experience with adversarial machine learning or rigorous security testing
Nice to Have
- Experience with large-scale model training or fine-tuning
- Knowledge of formal verification methods
- Contributions to open-source security tools or evaluations