Sr. Staff/Principal SW Security Engineer, AI Inference

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. Our novel wafer-scale architecture provides the AI compute power of dozens of GPUs on a single chip, with the programming simplicity of a single device. This approach allows Cerebras to deliver industry-leading training and inference speeds and empowers machine learning users to effortlessly run large-scale ML applications, without the hassle of managing hundreds of GPUs or TPUs.    Cerebras' current customers include top model labs, global enterprises, and cutting-edge AI-native startups.  OpenAI recently announced a multi-year partnership with Cerebras , to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.  Thanks to the groundbreaking wafer-scale architecture, Cerebras Inference offers the fastest Generative AI inference solution in the world, over 10 times faster than GPU-based hyperscale cloud inference services. This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation. About the Role   We’re looking for a Principal/Sr. Staff SW Security Software Engineer  to secure large-scale  AI inference infrastructure  running complex, high-performance workloads. You’ll design and implement security controls across the  entire inference stack  — from APIs and control planes to distributed systems, accelerators, and runtime environments. This role blends  systems engineering, platform security, and operational rigor in an environment where performance and reliability are mission critical. This is a hands-on engineering role with real ownership over production systems.     What You’ll Do   Architecting, implementing, and scaling robust security solutions for AI inference platforms   Lead and drive strategic security initiatives, fostering secure by default developer experiences, and mentoring high performing engineering teams. 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  (service isolation, mTLS, zero-trust patterns)   Harden inference runtimes, containers, and host systems   Develop protections against:   Model extraction   Prompt abuse   Data exfiltration   Supply-chain attacks   Build  secure key and secret management  systems   Partner with infra and ML teams to bake security into system design   Perform threat modeling and security reviews for new features   Lead incident response for security events related to inference systems     Core Engineering Qualifications 8+ years of strong software engineering background (not just policy or compliance)   Proficiency in one or more of:   Go, Rust, C++, Java, Python   Deep understanding of:   Distributed systems   Networking fundamentals   Linux internals     Security Experience   Experience securing  production infrastructure or platforms   Strong understanding of:   Authentication & authorization (OAuth, OIDC, RBAC, ABAC)   TLS, mTLS, cert management   Secure service-to-service communication   Hands-on experience with:   Secrets management   Key rotation   Secure boot / host hardening   Familiarity with:   Container security   Runtime isolation   Supply chain security (SBOMs, signing)     AI / Inference-Specific (Highly Valued)   Securing  model serving pipelines   Protecting inference APIs from:   Abuse   Denial of service   Model theft   Understanding of:   Multi-tenant inference environments   Hardware accelerators (GPUs, custom silicon)   Performance vs security tradeoffs   Experience working with ML or AI platform teams     Why Join Cerebras People who are serious about software make their own hardware. At Cerebras we have built a breakthrough architecture that is unlocking new opportunities for the AI industry. With dozens of model releases and rapid growth, we’ve reached an inflection  point in our business. Members of our team tell us there are five main reasons they joined Cerebras: Build a breakthrough AI platform beyond the constraints of the GPU. Publish and open source their cutting-edge AI research. Work on one of the fastest AI supercomputers in the world. Enjoy job stability with startup vitality. Our simple, non-corporate work culture that respects individual beliefs. Read our blog:  Five Reasons to Join Cerebras in 2026. Apply today and become part of the forefront of groundbreaking advancements in AI! Cerebras Systems is committed to creating an equal and