The posting
ABOUT THE ROLE
Serve as the primary technical interface between customers and engineering teams, helping integrate AI inference accelerators into production systems. This customer-facing role combines technical enablement, system-level troubleshooting, and collaboration across hardware and software teams.
WHAT YOU'LL DO
- Translate customer requirements and deployment challenges into actionable feedback for product and engineering teams.
- Support server manufacturers and platform partners as they integrate accelerators into production systems.
- Troubleshoot issues involving hardware, firmware, drivers, networking, thermals, and software interoperability.
- Manage customer escalations through resolution and keep stakeholders informed.
- Work with customers on AI framework compatibility, inference serving configurations, and data center deployments.
WHAT WE'RE LOOKING FOR
- Typically 5 to 10 or more years of experience in technical support, field application engineering, solutions engineering, customer engineering, or system integration.
- Hands-on background with AI infrastructure, inference serving, machine learning deployment, or data center platforms.
- Experience with Linux, containers, distributed systems, server architecture, PCIe accelerators, and data center infrastructure.
- Familiarity with PyTorch, ONNX, Hugging Face, vLLM, SGLang, Triton Inference Server, or equivalent tools.
- Strong debugging and problem-solving skills across hardware, firmware, drivers, and application software.
- Clear communication skills and experience working with OEMs, ODMs, hyperscalers, cloud providers, or enterprise customers.
LOCATION
On-site role based in the United States.



