Staff Software Engineer, Inference Platform

The role

This person will lead and contribute to projects on the Inference Platform team. They will own the orchestration layer that runs inference on datacenter clusters by connecting cloud components with machine learning services.

What you will do

• Design, develop, test, and maintain production software.
• Raise the effectiveness of senior engineers through design feedback, pairing, and clear technical standards.
• Help shape the technical direction for the Inference Platform and own the roadmap for major technical areas.
• Architect active-active systems with rapid failover, graceful degradation, and clear SLOs.
• Drive system-level improvements in latency, throughput, capacity efficiency, and resilience.
• Write and review production code in the most important parts of the platform.
• Lead on the hardest production issues and cross-system bottlenecks.
• Drive observability, incident response, capacity planning, and post-incident improvement.
• Partner with ML, Product, Infrastructure, and Cloud teams to translate requirements into scalable system designs.

Required qualifications

• 8+ years of experience in software engineering, 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 making sound architectural decisions for highly available, latency-sensitive systems at scale.
• Experience with security (certificates, TLS, mTLS).
• Experience optimizing latency, throughput, and efficiency in high-QPS systems.
• Strong proficiency in backend or systems languages such as Go or C++.
• Experience designing observability and reliability practices, including metrics, logging, tracing, alerting, incident response, and SLO-driven operations.
• Ability to influence senior engineers and cross-functional partners through technical credibility, communication, and judgment.

Nice to have

• Experience with TTFT and tail-latency reduction is a strong plus.
• Experience with ML inference infrastructure, model serving systems, or GPU-accelerated workloads.

About the company

Cerebras Systems builds the world's largest AI chip. The company works with leading model labs, global enterprises, and cutting-edge AI-native startups.