Staff Security Scientist: AI Safety & Privacy Research

Aptiora; San Francisco (CA); On-site; USD 160,000 - 230,000; Full time

Job summary

Perplexity's Secure Intelligence Institute (SII) seeks energetic researchers and engineers to advance security and privacy in frontier AI. You will identify threats, develop defenses, and build evaluation benchmarks for shipped AI systems.

Publish findings at top venues, collaborate with security engineers and external researchers, and translate research into concrete security features for Perplexity's platforms.

Qualifications

• PhD or equivalent research experience in CS/CE with focus on security/privacy.
• Publications in top security conferences (IEEE S&P, USENIX Security, ACM CCS, NDSS).
• Deep expertise in security of agentic systems, systems security, web/app security, program analysis, or software security.
• Proficiency in Python; TypeScript/Go/Rust a plus.
• Ability to work independently in a fast-paced environment and translate research into product.
• Clear and concise communication translating attack narratives into actionable insights.

Responsibilities

• Identify and analyze security/privacy threats across AI systems, infrastructure, and user-facing products.
• Develop novel defenses, mitigations, and detection mechanisms for security/privacy in AI-native products.
• Build security evaluation frameworks, benchmarks, and datasets to measure defense effectiveness.
• Partner with Security Engineering to translate research into shipped security features and hardened architectures.
• Collaborate with external researchers in SII's network.
• Publish findings at premier venues and contribute to the broader security research community.

Skills

Security research

Privacy research

Academic publishing

Independent researcher

Strong communication

Program analysis

Software security

Agentic systems security

Web security

Python

TypeScript

Go

Rust

Education

PhD in CS/CE or related field

Tools

Python

TypeScript

Go

Rust

Job description

Perplexity's Secure Intelligence Institute (SII) seeks energetic researchers and engineers to advance security and privacy in frontier AI. You will identify threats, develop defenses, and build evaluation benchmarks for shipped AI systems.

Publish findings at top venues, collaborate with security engineers and external researchers, and translate research into concrete security features for Perplexity's platforms.