Staff Software Engineer, Inference Platform

About the role

Cerebras Systems builds the world's largest AI chip, which delivers training and inference speeds over 10 times faster than GPU-based cloud services. The Inference Platform team owns the orchestration layer that runs inference on datacenter clusters, connecting cloud components with machine learning services. Cerebras is looking for a Staff Engineer to lead, drive and contribute to projects on this team, often solving problems that have not yet been solved.

Key responsibilities

• Design, develop, test and maintain production software across testing, continuous development, observability, security, networking, debugging and productionization.
• Help raise the effectiveness of senior engineers through design feedback, pairing and clear technical standards.
• Shape the technical direction of the Inference Platform, Kubernetes custom resource definitions, failure domains, service boundaries and system evolution, and own the roadmap for major technical areas.
• Architect active-active systems with rapid failover, graceful degradation and clear SLOs, improving latency, throughput, capacity efficiency and resilience.
• Write and review production code in critical parts of the platform, make high-consequence architectural decisions and set the technical bar through design and code reviews.
• Lead on hard production issues and cross-system bottlenecks, driving observability, incident response, capacity planning and post-incident improvement.
• Partner with ML, Product, Infrastructure and Cloud teams to turn product and business requirements into scalable system designs.

Required profile

• 8+ years of software engineering experience, with substantial individual contributor experience building and operating large-scale distributed systems or cloud infrastructure.
• Deep expertise in distributed systems architecture, ideally with Kubernetes.
• Strong track record of architectural decisions for highly available, latency-sensitive systems at scale.
• Ability to influence senior engineers and cross-functional partners through technical credibility and judgment.
• Preferred: experience with ML inference infrastructure, model serving systems or GPU-accelerated workloads; location in Sunnyvale or Toronto preferred.

Required skills

• Backend or systems languages such as Go or C++.
• Security (certificates, TLS, mTLS).
• Optimizing latency, throughput and efficiency in high-QPS systems; TTFT and tail-latency reduction is a strong plus.
• Observability and reliability practices: metrics, logging, tracing, alerting, incident response and SLO-driven operations.