AI Inference Core - Senior SDET, Release Integration Testing
Cerebras Systems2 days ago
Responsibilities
- Design, develop, and maintain automated test frameworks, tools, and infrastructure for AI inference software.
- Own integration testing and qualification activities for complex inference-core features, including dependency, interaction-risk, and coverage analysis.
- Develop and execute end-to-end, integration, regression, and system-level tests across frameworks, runtime, compiler, kernels, infrastructure, and hardware.
- Analyze test and benchmark results to assess release readiness and provide qualification recommendations.
- Investigate cross-stack failures, perform root cause analysis, collaborate on fixes, and implement regression-prevention tests.
- Improve master and release-branch stability through regression identification, failure triage, fix validation, and quality metrics.
- Build tooling for automation, diagnostics, monitoring, dashboards, CI/CD workflows, and release qualification pipelines.
- Contribute to test architecture, risk-based testing strategies, observability, automation efficiency, and release reliability.
- Provide technical guidance and mentorship to junior engineers through reviews and debugging sessions.
Requirements
- Professional experience developing software, automated testing frameworks, or test infrastructure.
- Proficiency in Python, Go, or a similar programming language with experience writing maintainable production-quality code.
- Experience designing, developing, and maintaining automated tests and frameworks for complex software systems.
- Strong debugging and problem-solving skills, including log analysis, system-behavior investigation, and root cause identification.
- Understanding of integration, system, regression, and end-to-end testing methodologies.
- Experience with CI/CD pipelines, test automation infrastructure, and software development workflows.
- Working knowledge of operating systems, networking, distributed systems, or systems-level software.
- Ability to independently own complex technical problems and drive issues through resolution.
- Strong communication and collaboration skills across multiple engineering teams.
- Preferred: experience with distributed systems, infrastructure software, runtime systems, compilers, kernels, AI/ML infrastructure, LLM inference, model deployment, multimodal workloads, hardware accelerators, GPU systems, or high-performance computing.
- Preferred: experience building scalable test frameworks, distributed test systems, release pipelines, or internal developer tools.
- Preferred: familiarity with performance testing, profiling, observability, fault injection, reliability engineering, production failure analysis, containers, Kubernetes, cloud infrastructure, or cluster orchestration.
Benefits
- Hybrid schedule with at least three days per week in the office; fully remote work is not available.
- Office locations are Sunnyvale, California, or Toronto, Ontario.
- Opportunity to work on a breakthrough AI platform, AI supercomputing, and cutting-edge AI research and open-source projects.
- Inclusive equal-opportunity workplace with continuous learning, growth, and team support.
Tech Stack
Categories
About Cerebras Systems
Cerebras Systems designs and sells AI compute systems built around its wafer-scale WSE-3 processor, delivered as the CS-3 appliance and via the Cerebras Cloud. It targets enterprises, model labs, and government users needing fast training and inference, and offers on‑prem and cloud deployments. Privately held and headquartered in Sunnyvale, California, the company announced a multi-year partnership with OpenAI to deploy large-scale inference capacity.