About the Role
This position leads the development and implementation of security measures tailored to AI platforms, working cross-functionally to integrate safeguards into machine learning models and data pipelines.
Responsibilities
- Design and deploy security frameworks for AI and machine learning systems
- Identify and address vulnerabilities specific to AI infrastructure
- Collaborate with research and engineering teams to embed security in AI development
- Evaluate risks associated with data sourcing and model training
- Develop policies for secure model deployment and monitoring
- Lead threat modeling exercises for AI-powered applications
- Ensure compliance with data privacy regulations in AI workflows
- Create tools to detect adversarial attacks on machine learning models
- Guide secure integration of third-party AI components
- Establish best practices for model interpretability and auditability
- Monitor emerging threats in the AI domain
- Support incident response for AI-related security breaches
- Contribute to secure software development lifecycle enhancements
- Mentor engineers on AI security principles
- Publish insights on AI security challenges and solutions
Nice to Have
- Advanced degree in computer science, cybersecurity, or related discipline
- Direct experience securing large-scale AI deployments
- Publications or presentations in AI security domains
- Contributions to open-source AI security tools
- Knowledge of regulatory frameworks for AI governance
Compensation
Competitive salary, equity, and benefits package commensurate with experience
Work Arrangement
Hybrid work model with flexibility based on location
Team
Part of the security engineering team focused on emerging technology risks
Why This Role Matters
AI systems introduce novel security challenges that require specialized expertise. This role ensures that intelligent technologies are built and operated with strong defenses against evolving threats, protecting both systems and users.
What We Value
Technical depth, proactive problem solving, collaboration across disciplines, clear communication, and a commitment to ethical AI practices.
Available for qualified candidates in select regions
