Principal AI Security & Risk Researcher

Ciph Lab | Remote | Equity-Only (Pre-Seed)

About Ciph Lab

Ciph Lab is building Intelligence Resources™—software that operationalizes responsible AI governance 're a 4-month-old AI governance company, AI-first and remote-first, transitioning from consultancy to agents and SaaS platform.

AI security isn't static—new jailbreaks, prompt injections, and model vulnerabilities emerge constantly. Traditional security assessments can't keep pace. We're building adaptive governance systems with security-by-design that evolve as the threat landscape changes.

We're seeking a Principal AI Security & Risk Researcher to join our founding research team and lead our security track. This isn't traditional red teaming or pentesting—you'll be designing continuous security monitoring systems and building frameworks that help enterprises assess and mitigate AI risks at scale.

You’ll research emerging AI threats (jailbreaks, prompt injections, model vulnerabilities), translate findings into actionable security frameworks, and collaborate with our technical team to build automated security testing and audit telemetry.

This is a founding research role with equity ownership in defining how organizations approach AI security.

• Research emerging AI attack vectors, guardrail bypasses, and defense mechanisms
• Monitor threat intelligence feeds and security research communities
• Experiment with new AI security tools and assessment methodologies
• Stay current with LLM vulnerabilities, adversarial techniques, and model safety

• Design security assessment frameworks for generative AI and agentic systems
• Develop risk evaluation methodologies that adapt as threats evolve
• Create audit telemetry and security monitoring protocols
• Translate security research into operational frameworks that enterprises can deploy

• Collaborate with the technical team to build automated security testing tools
• Design continuous threat monitoring and alerting systems
• Create security validation processes for framework updates
• Ensure monitoring systems themselves are secure (meta-security)
• Build audit trails for compliance documentation

• Contribute to Ciph Lab's weekly newsletter on AI security and risk
• Position the company as a trusted voice in AI security governance
• Share insights publicly (while protecting proprietary methods)

• 5+ years in cybersecurity, with 2+ years focused on AI/ML security, red teaming, or adversarial testing
• Deep understanding of LLM architectures, prompt injection, jail breaking, and model safety mechanisms
• Experience developing security testing frameworks or vulnerability assessment tools
• Strong research capabilities with ability to translate technical findings into actionable frameworks

• Experience with AI governance frameworks (NIST AI RMF, ISO 42001, EU AI Act)
• Background in enterprise risk assessment or security audit methodologies
• Familiarity with agent architectures, RAG systems, or multi-modal AI security
• Published work in AI security, adversarial ML, or related fields

• Self-directed: You identify threats proactively, set research priorities, drive security strategy without oversight
• Systems thinker: You see how security connects to governance, compliance, and technical implementation
• Continuous learner: You stay ahead of rapidly evolving AI threats and defense mechanisms
• Collaborative: You work effectively with legal, governance, and technical experts
• Disciplined remote worker: You manage time effectively, maintain momentum on long-term research, and show up consistently

• You’re building adaptive security infrastructure
  , not just finding vulnerabilities
• You work at the intersection of AI security, governance, and compliance
• You’re designing living security frameworks that update as threats emerge
• You’re shaping standards in an emerging field with limited precedent

• Remote-first, manage your own schedule
• Weekly team meetings (Wednesdays 5-6 pm PT)
• Async collaboration via Slack and shared tools
• 5-10 hours/week…