AI Safety Engineer

Join Cisco's Enterprise AI team as an AI Safety Engineer. You'll connect AI safety research with production engineering, developing methods and infrastructure to assess model behavior and ensure deployed AI systems remain reliable and aligned.

Your Impact You'll operationalize transparency by translating concepts from mechanistic interpretability into scalable pipelines. You'll build infrastructure to extract, map, and interpret model activations and latent representations. You'll design red-teaming frameworks and automated behavioral auditing stress tests to identify misalignment and risks.

Minimum Qualifications

• Bachelor's + 7 years of related experience, or Master's + 4 years, or PhD + 1 year, or equivalent experience
• Hands-on experience deploying or operating machine learning models in production using Python
• Demonstrated ability to conduct empirical work and communicate technical results
• Practical understanding of transformer-based language models and alignment approaches
• Proficiency in building evaluation frameworks for model reliability and safety

Preferred Qualifications

• High proficiency in Python frameworks and distributed training environments
• Experience probing, mapping, or analyzing model activations and internal states
• Hands-on experience with container orchestration, CI/CD tools, and model tracking tools
• Familiarity with information security principles and structured threat modeling
• Experience applying methods for eliciting model knowledge and evaluating output divergence

Benefits

• Medical, dental, and vision insurance
• 401(k) plan with Cisco matching contribution
• Paid parental leave, short and long-term disability coverage, and basic life insurance
• Paid time away, including holidays, birthday, and personal wellness days
• Flexible vacation time off program
• Optional 10 paid days per year to volunteer