Staff Engineer, Inference Platform & Kubernetes at Scale

Cerebras; Sunnyvale (CA); On-site; CAD 150,000 - 210,000; Full time

Job summary

Cerebras Systems is hiring a Staff Engineer to lead on the Inference Platform, directing projects that orchestrate inference on datacenter clusters. You will work across Kubernetes operators, security policies, and CI/CD to drive scalable, secure systems.

The role emphasizes architectural leadership, reliability, and performance as Cerebras builds a globally distributed inference platform, with teams spanning ML, product, and cloud disciplines.

Qualifications

• 8+ years of software engineering experience with large-scale distributed systems or cloud infrastructure.
• Strong expertise in distributed systems architecture, ideally with Kubernetes.
• Track record of designing high-availability, low-latency systems at scale.
• Experience with security (certificates, TLS, mTLS).
• Experience optimizing latency, throughput, and efficiency in high-QPS systems.

Responsibilities

• Design, develop, test, and maintain production software across testing, CI/CD, and observability.
• Provide architectural guidance and raise standards through reviews and mentoring.
• Shape the Inference Platform technical direction and own roadmap for key areas.
• Architect active-active systems with rapid failover and clear SLOs; improve latency and capacity efficiency.
• Lead on production issues, incidents, and cross-system bottlenecks with strong operational rigor.
• Collaborate with ML, Product, Infrastructure, and Cloud teams to align on technical decisions.

Skills

Distributed systems

Kubernetes

Go/C++

Security TLS mTLS

Observability

Latency optimization

Cross-functional influence

ML inference infra

Job description

Cerebras Systems is hiring a Staff Engineer to lead on the Inference Platform, directing projects that orchestrate inference on datacenter clusters. You will work across Kubernetes operators, security policies, and CI/CD to drive scalable, secure systems.

The role emphasizes architectural leadership, reliability, and performance as Cerebras builds a globally distributed inference platform, with teams spanning ML, product, and cloud disciplines.