Staff Software Engineer Inference Cloud
Posted Updated 6
views
Summary
Staff engineer owning major areas of Cerebras's cloud-platform architecture for AI inference services: designing distributed components (routing, load balancing, caching, failover), writing production code, leading incident response and capacity planning, and mentoring senior engineers. Core stack involves Go, C++, or Python and large-scale multi-region distributed systems.
You will own major areas of cloud-platform architecture for inference services. You will build distributed platform components, improve traffic control and reliability, write and review production code, resolve critical production issues, drive observability and capacity planning, and mentor senior engineers.
Responsibilities
- Shape platform direction for multi-region topology, failure domains, service boundaries, and system evolution
- Design and build service discovery, request routing, load balancing, caching, batching, and traffic-management components
- Architect active-active systems with failover, graceful degradation, and SLOs
- Define admission control, quota management, rate limiting, and quality-of-service mechanisms
- Write and review production code on critical platform paths
- Lead production issue resolution, observability, incident response, capacity planning, and post-incident improvement
- Translate requirements into scalable system designs with adjacent teams
- Mentor senior engineers through design feedback, pairing, and technical standards
Requirements
- 8+ years of software engineering experience
- Experience building and operating large-scale distributed systems or cloud infrastructure
- Expertise in distributed systems architecture, networking, compute orchestration, container platforms, and multi-region production services
- Experience making architectural decisions for highly available, latency-sensitive systems
- Experience optimizing latency, throughput, and efficiency in high-QPS systems
- Proficiency in Go, C++, or Python
- Experience with metrics, logging, tracing, alerting, incident response, and SLO-driven operations
- Ability to influence senior engineers and cross-functional partners
