Deployment Engineer, AI Inference

Cerebras Systems

82d

About The Position

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. Our novel wafer-scale architecture provides the AI compute power of dozens of GPUs on a single chip, with the programming simplicity of a single device. This approach allows Cerebras to deliver industry-leading training and inference speeds and empowers machine learning users to effortlessly run large-scale ML applications, without the hassle of managing hundreds of GPUs or TPUs. Cerebras' current customers include global corporations across multiple industries, national labs, and top-tier healthcare systems. In January, we announced a multi-year, multi-million-dollar partnership with Mayo Clinic, underscoring our commitment to transforming AI applications across various fields. In 2024, we launched Cerebras Inference, the fastest Generative AI inference solution in the world, over 10 times faster than GPU-based hyperscale cloud inference services.

Requirements

• 5-7 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.

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.

Benefits

• Job stability with startup vitality
• Opportunity to work on one of the fastest AI supercomputers in the world
• Non-corporate work culture that respects individual beliefs
• Ability to publish and open source cutting-edge AI research
• Build a breakthrough AI platform beyond the constraints of the GPU

What This Job Offers

• Number of Employees: 251-500 employees