Senior Staff Software Engineer Inference Platform
Cerebras builds wafer-scale AI computing systems and a cloud inference platform for training, fine-tuning, and serving AI models.
About Cerebras Systems, Inc.
Cerebras Systems is an AI-infrastructure company founded in 2015. It sells rack-scale wafer-scale computing systems and provides cloud-based, API-accessible AI inference alongside on-premises deployments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead the design, development, testing, and operation of inference-platform software. You will set technical direction, improve active-active system reliability and performance, guide senior engineers, make critical architectural decisions, and drive observability, incident response, capacity planning, and cross-functional alignment.
Requirements
- 8+ years of software engineering experience
- Large-scale distributed systems or cloud infrastructure
- Distributed-systems architecture
- Kubernetes
- Highly available latency-sensitive systems
- Security
- Certificates
- TLS
- mTLS
- High-QPS system optimization
- Go or C++
- Observability
- Metrics
- Logging
- Tracing
- Alerting
- Incident response
- SLO-driven operations
- Technical communication
Responsibilities
- Design, develop, test, and maintain production software
- Raise senior-engineer effectiveness through design feedback, pairing, and technical standards
- Shape platform direction, Kubernetes custom resource definitions, failure domains, service boundaries, and technical roadmaps
- Architect active-active systems with failover, graceful degradation, and service-level objectives
- Improve latency, throughput, capacity efficiency, and resilience
- Write and review code for critical platform paths and make architectural decisions
- Lead production issue resolution, observability, incident response, and capacity planning
- Translate requirements into scalable system designs and align shared technical decisions
