- United States
- On-site
- Full-time · Senior
- 5–10 years
Serve as the primary technical interface between customers and engineering teams, helping integrate AI inference accelerators into production systems.
Responsibilities
- 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.
Requirements
- Nice to have: PyTorch
- Nice to have: ONNX
- Nice to have: Hugging Face
- Nice to have: vLLM
- Nice to have: SGLang
