Senior Staff Engineer, Inference Platform (Distributed AI)

Cerebras Systems; Sunnyvale (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Cerebras Systems is seeking a Staff Engineer to lead the Inference Platform team, owning orchestration across datacenter clusters and connecting cloud components with ML services. You will solve hard problems in Kubernetes operators, security policies, and CI/CD, driving architectural direction and platform roadmap.

The role emphasizes latency, reliability, and scalability, with production code contributions and cross-functional collaboration with ML, Infrastructure, and Cloud teams to deliver

Qualifications

• 8+ years of software engineering experience in large-scale distributed systems or cloud infrastructure.
• Strong architecture experience for highly available, latency-sensitive systems.
• Experience with security (certificates, TLS, mTLS).
• Experience with ML inference infrastructure or GPU-accelerated workloads is a plus.

Responsibilities

• Design, develop, test, and maintain production software across testing, CI/CD, observability, security, networking, and productionization.
• Raise effectiveness of senior engineers through design reviews, pairing, and clear standards.
• Shape the technical direction for the Inference Platform, Kubernetes CRDs, failure domains, and roadmaps for major areas.
• Architect active-active systems with rapid failover and clear SLOs, improving latency and throughput.
• Lead on production issues and cross-system bottlenecks, driving incident response and capacity planning.
• Collaborate with ML, Product, Infrastructure, and Cloud teams to translate requirements into scalable designs.

Skills

Kubernetes

Distributed systems

Go/C++ production code

Observability

SLOs & latency

Security TLS/mTLS

Cross-functional influence

Production reliability

High availability

ML inference infrastructure

Tools

Kubernetes

Job description

Cerebras Systems is seeking a Staff Engineer to lead the Inference Platform team, owning orchestration across datacenter clusters and connecting cloud components with ML services. You will solve hard problems in Kubernetes operators, security policies, and CI/CD, driving architectural direction and platform roadmap.

The role emphasizes latency, reliability, and scalability, with production code contributions and cross-functional collaboration with ML, Infrastructure, and Cloud teams to deliver