AI Inference Core - Junior SDET, Release Integration Testing

Job Title

AI Inference Core - Junior SDET, Release Integration Testing

Role Summary

Early-career Software Development Engineer in Test (SDET) on the Release Integration Testing (RIT) team for the AI Inference Core. Develop automation, validate model and platform capabilities across the inference stack, triage integration and release issues, and help maintain master and release branch stability.

Work spans AI frameworks, runtime, compiler, kernels, distributed systems, infrastructure, and hardware; collaborate with feature teams and release owners to deliver integration evidence and improve release readiness.

Experience Level

Entry-level / Early-career — suitable for candidates with internships, academic projects, research, open-source contributions, or up to 0–3 years of hands-on software or testing experience.

Responsibilities

The RIT SDET is responsible for integration testing, automation, and release support.

• Design, implement, and maintain automated tests for models, features, integration, regression, and releases.
• Run cross-stack end-to-end workflows and collect unit, simulation, benchmark, and integration evidence.
• Triaging failures on master and release branches; identify owners, validate fixes, and verify closure.
• Write test automation, diagnostics, testbeds, data-analysis scripts, dashboards, and release pipelines using Python, Go, or similar languages.
• Collaborate with Integration, Core Infra, and feature teams to reproduce issues and route coverage gaps appropriately.
• Document test intent and findings and grow toward independent ownership of a test domain.
• Improve automation efficiency, metrics, probes, diagnostics, and roadmap test plans between engagements.

Requirements

Must-have technical skills and behaviors.

• Proficient in programming with Python, Go, or a similar language.
• Hands-on experience building, testing, or debugging software via internships, projects, open source, or professional work.
• Basic understanding of data structures, algorithms, operating systems, networking, or distributed-systems concepts.
• Strong debugging skills: break down problems, form hypotheses, gather evidence, and learn from results.
• Comfort reading unfamiliar code, learning new stack layers, and taking ownership with mentorship.
• Clear written and verbal communication, collaboration, persistence, and ability to work through ambiguity.

Nice-to-have

• Experience or coursework in testing, distributed systems, compilers, operating systems, computer architecture, or AI systems.
• Experience building test frameworks, CI workflows, developer tools, or automation for data analysis.
• Exposure to software/hardware co-design, hardware accelerators, performance debugging, containers, or cloud deployments.
• Familiarity with observability tools (logs, metrics, profilers) and model deployment / LLM workloads.
• Demonstrated initiative through substantial projects, tooling, or open-source contributions.

Education Requirements

Not specified.

About the Company

Company: Cerebras

Headquarters: Sunnyvale, CA, USA

Developer of wafer-scale AI accelerators, Cerebras designs the Wafer Scale Engine (WSE)—one of the world’s largest AI chips—to deliver high-speed training and inference solutions for model labs, enterprises, and AI-native startups.