About the job
OpenAI’s Hardware organization develops AI-native silicon and system-level solutions for the unique demands of advanced AI workloads. Building on efforts like Jalapeño, the team is developing future generations of AI-native silicon and tightly integrated systems to power the next generation of frontier models. By co-designing chips, systems, tools, and methodologies, the team helps deliver faster, more efficient, and production-ready hardware for OpenAI’s supercomputing platform.
Responsibilities
- Work on Machine Learning/AI hardware system projects to craft solutions for current and future data center deployments
- Design, implement, and execute comprehensive test plans that ensure the reliability, performance, and scalability of supercomputing hardware systems
- Develop detailed test plans and methodologies tailored to hardware components, including processors, memory modules, custom accelerators and interconnects
- Collaborate with hardware design, manufacturing, firmware teams and vendors to identify, analyze, and resolve issues affecting hardware, power, thermal and high-speed interconnects
- Perform in-depth debugging on the hardware system and assess signal integrity, error rates, and overall link performance for high-speed links with a focus on SerDes technology
- Collaborate with the lab manager to maintain equipment and hardware systems, including oscilloscopes, thermal test chambers, liquid cooling systems, and other measurement devices
- Utilize advanced diagnostic and measurement tools to capture performance metrics and analyze system behavior
- Develop and maintain automation scripts to streamline testing processes using Python, Bash and test automation frameworks
Qualifications
Minimum
- At least 10 years of industry experience, including experience testing or supporting hardware design teams for datacenter applications
- Proven experience in hardware testing and validation, with hands-on experience with oscilloscopes, power supplies, analyzers, and other test instruments
- Strong understanding of electrical, power and thermal testing methodologies
- Expertise with protocol of common interfaces such as SPI, I2C, USB, DDRx, and experience characterizing and verifying compliance of Datacenter Ethernet interfaces
- Hands-on experience with high-speed electrical and thermal test equipment such as oscilloscopes, VNA, TDR, thermal cameras, heat sinks, and test chambers
- Experience in using Cadence Allegro and automation / scripting
- Experience and good knowledge of system testing from xPUs, board, rack level to data center level
- Excellent analytical, problem-solving, and troubleshooting skills
Preferred
- Proficiency in Python, Bash and test automation frameworks to develop automated test scripts