Inference ML API SDET
Cerebras Systems2 months ago
Responsibilities
- Architect and own end-to-end test strategies, scalable tests, frameworks, and tooling for new ML API features.
- Lead testing and validation of AI/ML models, including accuracy, fairness, performance, integration, and production readiness.
- Drive benchmark contributions, evaluation methodologies, automation initiatives, test coverage, and risk-based testing decisions.
- Debug complex issues across distributed, scaled-out deployments and identify systemic quality gaps.
- Lead cross-functional quality initiatives and technical communication across engineering, product, customer operations, field teams, and time zones.
- Mentor junior SDETs on testing methodology, debugging practices, and automation development.
Requirements
- 5+ years of relevant industry experience in software integration, development, or quality engineering.
- Deep automation and programming expertise in one or more of Python, C++, or Go, with the ability to build reusable test frameworks.
- Experience testing compute, machine learning, networking, or storage systems in large-scale enterprise environments.
- Strong debugging experience across distributed, scaled-out deployments.
- Experience leading cross-functional quality initiatives and mentoring engineers across geographically dispersed teams.
- Strong verbal and written communication, organizational skills, ownership, and independent project execution.
- Preferred: experience with LLM or multimodal training or inference, hardware architecture, performance optimization, compilers, and ML frameworks.
- Preferred: experience with distributed systems, cloud infrastructure, security validation, microservices deployment, debugging, orchestration, and quality engineering culture or test infrastructure.
Benefits
- Hybrid schedule requiring in-office presence three days per week; fully remote is not available.
- Office locations are Sunnyvale, California, and Toronto, Canada.
- Opportunity to work on Cerebras’s AI platform and high-speed inference systems.
- Opportunities to publish and open-source AI research and work on a large-scale AI supercomputer.
- The company describes job stability, startup vitality, and a non-corporate culture focused on individual beliefs, learning, growth, and support.
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.