Brings up Cerebras' next-generation AI hardware systems and supporting software infrastructure: debugging hardware-software interactions, root-causing bring-up failures, and building automation, testing, and observability tooling. Core stack is Python/C++ on Linux, spanning distributed hardware, networking, and telemetry.
You will bring up AI hardware systems and supporting software infrastructure. You will debug hardware and software interactions, investigate failures, identify root causes, and build automation and test frameworks. You will improve observability, validate new hardware generations, and improve debugging and testing workflows.
Responsibilities
Participate in bring-up of next-generation AI hardware systems and supporting software infrastructure
Debug system-level hardware and software issues
Investigate bring-up failures and identify root causes using logs, telemetry, and diagnostic tools
Build automation frameworks and internal tooling for validation and debugging
Develop software to test, validate, and stress distributed hardware systems
Collaborate with hardware engineers to resolve system integration issues
Build observability tools that surface failures and accelerate debugging
Reproduce, triage, and diagnose issues during early hardware deployment
Support validation and qualification of new hardware generations
Improve debugging, testing, and automation workflows
Requirements
Programming skills in Python or C++
Debugging and problem-solving skills
Knowledge of operating systems, processes, threads, memory management, concurrency, and IPC
Experience with Linux development environments
Knowledge of computer architecture and hardware-software interactions
Analytical root-cause analysis
Communication skills
Experience building automation frameworks, internal tooling, or test infrastructure