Inference Platform Engineer — Build Scalable AI Infra

Cerebras Systems

Sunnyvale (CA)

On-site

USD 180,000 - 240,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Cerebras Systems in Sunnyvale or Toronto is seeking a Software Engineer to contribute to the Inference Platform that runs on our datacenter clusters. You will help connect cloud components with ML services, focusing on orchestration, security, and CI/CD to ship reliable software.

Join a team that tackles first-of-its-kind problems, shapes platform direction, and leads critical production initiatives. You will work across Kubernetes operators, performance tuning, and cross-team collaborations to

Qualifications

3+ years of software engineering with distributed systems or cloud infrastructure.
Experience with Kubernetes and large-scale deployments.
Experience building latency-sensitive, highly available systems.
Strong backend language skills in Go or C++.

Responsibilities

Design, develop, test, and maintain production software spanning testing, continuous development, observability, security, networking, debugging and productionization.
Shape the technical direction for the Inference Platform, Kubernetes CRDs, failure domains and system evolution; own major roadmaps.
Architect active-active systems with rapid failover, graceful degradation and clear SLOs; improve latency, throughput and resilience.
Write and review production code; set the technical bar through design/code reviews and engineering judgment.
Lead on the hardest production issues and cross-system bottlenecks; drive incident response and capacity planning.
Collaborate with ML, Product, Infrastructure and Cloud teams to translate requirements into scalable designs.