AI Security Researcher/Research Engineer
Core
Design and implement secure-by-design architectures for LLM-powered web agents and chatbots, conducting adversarial evaluations and developing security-focused training techniques.
Role type
Senior IC AI Security Researcher (LLM security)
Builds
Secure LLM-powered web agents and chatbots for Brave's private browser and search
Domain
AI Security / Large Language Models / Web Agents
Deliverable
production ML models
Required skills
Adversarial evaluation design, LLM security (prompt injection, tool abuse), model behavior analysis, security-focused fine-tuning, Python, PyTorch/JAX, LLM training and evaluation, information flow control, access control
Preferred skills
Secure AI guardrails, confidential computing, ZKP/SMPC protocols, top-tier Ph.D. in CS, premier publication record
Technologies
PyTorch, JAX, LLM frameworks
Responsibilities
Design and execute adversarial evaluations to uncover failure modes in LLM-powered web agents; Analyze model behavior to forecast security risks; Develop and prototype security-focused training and fine-tuning techniques; Augment web agents with security principles like information flow control; Partner with engineers and researchers to translate findings into product changes; Help define forward-looking security strategy and policy for web agents
Seniority
Senior, hands-on IC