Apply on Employer Site

Cerebras · 2 days ago

Deployment Engineer, AI Inference

Sunnyvale CA or Toronto Canada

Full-time

Onsite

Entry, Mid Level

2+ years exp

Cerebras Systems builds the world's largest AI chip, focusing on providing industry-leading training and inference speeds for machine learning applications. The Deployment Engineer will be responsible for deploying and operating AI inference clusters, ensuring reliable and efficient deployment of workloads across their global infrastructure.

Artificial Intelligence (AI)ComputerHardwareSemiconductorSoftware

Growth Opportunities

Responsibilities

Deploy AI inference replicas and cluster software across multiple datacenters

Operate across heterogeneous datacenter environments undergoing rapid 10x growth

Maximize capacity allocation and optimize replica placement using constraint-solver algorithms

Operate bare-metal inference infrastructure while supporting transition to K8S-based platform

Develop and extend telemetry, observability and alerting solutions to ensure deployment reliability at scale

Develop and extend a fully automated deployment pipeline to support fast software updates and capacity reallocation at scale

Translate technical and customer needs into actionable requirements for the Dev Infra, Cluster, Platform and Core teams

Stay up to date with the latest advancements in AI compute infrastructure and related technologies

Qualification

PythonLinux systemsDockerKubernetesTelemetryOn-prem compute infrastructureObservabilitySpine-leaf networkingOwnership mindsetFast-paced environment

Required

2-5 years of experience in operating on-prem compute infrastructure (ideally in Machine Learning or High-Performance Compute) or developing and managing complex AWS plane infrastructure for hybrid deployments

Strong proficiency in Python for automation, orchestration, and deployment tooling

Solid understanding of Linux-based systems and command-line tools

Extensive knowledge of Docker containers and container orchestration platforms like K8S

Familiarity with spine-leaf (Clos) networking architecture

Proficiency with telemetry and observability stacks such as Prometheus, InfluxDB and Grafana

Strong ownership mindset and accountability for complex deployments

Ability to work effectively in a fast-paced environment