Senior Principal Engineer - Inference Cloud

Cerebras Systems; Sunnyvale (CA); On-site; USD 230,000 - 340,000; Full time

Job summary

Cerebras Systems is seeking a Principal Engineer for the Inference Cloud Platform in Sunnyvale, CA. You will own the cloud layer behind our Inference Service, ensuring availability, latency, and multi-region scale.

This role requires defining architecture, setting direction across teams, and contributing production code on critical paths. You’ll frame ambiguous problems, trade off options, and drive execution with strong technical judgment.

Qualifications

• 10+ years of software engineering, with IC experience building and operating large-scale distributed systems.
• Deep expertise in distributed systems architecture in cloud environments, including networking, compute orchestration, container platforms, and multi-region production services.
• Strong track record of architectural decisions for highly available, latency-sensitive systems at scale, demonstrated by systems you built.
• Experience optimizing latency, throughput, and efficiency in high-QPS systems; TTFT and tail-latency reduction is a strong plus.
• Strong proficiency in backend or systems languages such as Go, C++, or Python, with ability to contribute production code.
• Experience designing observability and reliability practices, including metrics, logging, tracing, alerting, incident response, and SLI/SLO/SLA-driven operations.
• Ability to influence senior engineers, technical leads, and cross-functional partners through technical credibility, communication, and judgment.
• Experience with ML inference infrastructure, model serving systems, or GPU-accelerated workloads is a plus.

Responsibilities

• Problem Definition & Prioritization. Identify the most important technical problems for the platform, often before there is a clear ask. Make explicit tradeoffs about platform scope with reasoning that holds up to scrutiny.
• Platform Direction. Set long-term technical direction for the Inference Cloud Platform, including multi-region topology and service boundaries.
• Reliability & Performance. Architect active-active systems with rapid failover and graceful degradation; drive latency, throughput, capacity, and resilience improvements.
• Code & Design Reviews. Contribute production code in critical paths and guide architectural decisions including build-vs-buy tradeoffs.
• Production Leadership. Lead on hard production issues, drive observability, incident response, and post-incident improvements.
• Technical Strategy Beyond Your Team. Shape platform-wide decisions on reliability, API design, capacity planning, and deployment strategies.
• Mentorship. Raise the quality of technical decision-making through design feedback and engineering standards.

Skills

Distributed systems

Cloud infrastructure

Go / C++ / Python

Observability & SRE

Multi-region architecture

Production code

Job description

Cerebras Systems is seeking a Principal Engineer for the Inference Cloud Platform in Sunnyvale, CA. You will own the cloud layer behind our Inference Service, ensuring availability, latency, and multi-region scale.

This role requires defining architecture, setting direction across teams, and contributing production code on critical paths. You’ll frame ambiguous problems, trade off options, and drive execution with strong technical judgment.