Cerebras
Senior Inference ML API SDET
Sunnyvale, CA. Posted 4 months ago
The role
You will lead testing strategy and execution for AI/ML models, evaluating accuracy, fairness, and performance at scale. You will deliver and validate software and hardware components for Cerebras API Features.
What you will do
- Architect and own end-to-end test strategies for new features.
- Develop scalable tests, frameworks, and tooling.
- Lead contributions to industry-standard benchmarks.
- Drive adoption of rigorous evaluation methodologies.
- Define and drive automation initiatives.
- Make strategic decisions around coverage trade-offs and risk-based testing priorities.
- Mentor and guide junior SDETs.
- Identify systemic quality gaps and drive cross-functional initiatives.
- Lead and facilitate technical communication across teams and time zones.
Required qualifications
- 5+ years of relevant industry experience in software integration, development, or quality engineering.
- Deep expertise in automation and programming using Python, C++, or Go.
- Ability to design and build reusable test frameworks from the ground up.
- Proven experience testing compute, machine learning, networking, or storage systems within large-scale enterprise environments.
- Strong track record of debugging complex issues across distributed, scaled-out deployments.
- Demonstrated ability to lead cross-functional quality initiatives.
- Excellent verbal and written communication skills.
- Experience presenting technical findings to engineering and leadership audiences.
- Strong organizational skills and ownership mindset.
- Experience leading and mentoring engineers across geographically dispersed teams and time zones.
Nice to have
- Hands-on experience with ML workloads including LLM and/or multimodal training or inference.
- Deep familiarity with hardware architecture, performance optimizations, compilers, and ML frameworks.
- Experience designing test strategies for distributed systems, cloud infrastructure, and security validation.
- Experience with microservices deployment, debugging, and orchestration at scale.
- Prior experience owning or significantly contributing to a team's quality engineering culture or test infrastructure.
About the company
Cerebras Systems builds the world's largest AI chip. The company works with leading model labs, global enterprises, and cutting-edge AI-native startups.