Principal SW Security Engineer, AI Inference

Cerebras Systems

about 3 hours ago

Sunnyvale, CA, USA or Toronto, Canada

Staff+

H1B Sponsor

Responsibilities

Design and implement security architectures for AI inference platforms.
Secure model serving, APIs, and control planes against abuse and attacks.
Build authentication, authorization, and identity systems for internal and external services.
Implement network security including service isolation and zero-trust patterns.
Harden inference runtimes, containers, and host systems.
Develop protections against model extraction, prompt abuse, data exfiltration, and supply-chain attacks.
Build secure key and secret management systems.
Partner with infrastructure and ML teams to integrate security into system design.
Perform threat modeling and security reviews for new features.
Lead incident response for security events related to inference systems.

10+ years of strong software engineering background.
Proficiency in one or more programming languages such as Go, Rust, C++, Java, or Python.
Deep understanding of distributed systems and networking fundamentals.
Experience securing production infrastructure or platforms.
Strong understanding of authentication and authorization mechanisms.
Hands-on experience with secrets management and secure service-to-service communication.
Familiarity with container security and runtime isolation.
Experience working with ML or AI platform teams is highly valued.

Opportunity to build a breakthrough AI platform beyond GPU constraints.
Ability to publish and open source cutting-edge AI research.
Work on one of the fastest AI supercomputers in the world.
Enjoy job stability with startup vitality.
Experience a simple, non-corporate work culture that respects individual beliefs.

C++GoJavaLinuxPythonRust