Senior Reliability Engineer, AI Inference at Scale

Cerebras; Raleigh (NC); On-site; USD 170,000 - 250,000; Full time

Job summary

Cerebras Systems is seeking a hands-on Reliability Tech Lead to own the mission of making Cerebras Inference the most reliable AI service. You will establish SLOs and drive reliability across the inference stack, from client SDKs to data-center deployments.

You will define incident-response frameworks, design scalable reliability mechanisms, and collaborate with hundreds of engineers to uphold world-class reliability standards.

Qualifications

• 7+ years of backend, infrastructure, or reliability engineering for large-scale distributed systems.
• Strong programming skills in Python, C++, Go, or Rust.
• Deep experience with reliability: SLO/SLI/SLA design, incident response, postmortem culture.
• Excellent communication and cross-functional leadership skills.
• Bonus: experience building large-scale AI infrastructure systems.

Responsibilities

• Define and drive reliability strategy: establish SLOs and ensure alignment across engineering.
• Design and implement reliability mechanisms: build, evolve systems for fault detection, degradation, failover, throttling, and recovery across multiple regions and data centers.
• Lead large-scale incident management: own postmortems, root-cause analysis, and prevention loops for reliability incidents.
• Architect for reliability and observability: influence system design for redundancy, durability, and debuggability.
• Develop reliability tooling: create internal tools and frameworks for chaos testing, load simulation, and distributed fault injection.
• Collaborate broadly: work across software, infrastructure, and hardware teams to embed reliability across layers of the inference service.
• Monitor and communicate reliability metrics: build dashboards and alerts for service health and actionable insights.
• Mentor and influence: guide engineers and share best practices for designing, testing, and operating reliable large-scale systems.

Skills

Backend engineering

Distributed systems

SLO/SLI design

Incident response

Leadership

Python

C++

Go

Rust

Education

Bachelor's degree in CS

Master's degree in CS

Job description

Cerebras Systems is seeking a hands-on Reliability Tech Lead to own the mission of making Cerebras Inference the most reliable AI service. You will establish SLOs and drive reliability across the inference stack, from client SDKs to data-center deployments.

You will define incident-response frameworks, design scalable reliability mechanisms, and collaborate with hundreds of engineers to uphold world-class reliability standards.