About this role
About the Role
Join a growing US team as the primary technical interface between customers and engineering. You will help integrate AI inference accelerators into production systems, combining customer enablement, technical support, and system-level troubleshooting.
What You'll Do
- Translate customer requirements and deployment challenges into actionable feedback for product and engineering teams.
- Help server manufacturers and platform partners integrate accelerators into production systems, resolving hardware, firmware, driver, networking, and thermal issues.
- Lead post-sale technical engagements covering chip integration, benchmarking, software enablement, and configuration.
- Manage customer escalations through resolution and keep stakeholders informed.
- Work with validation, runtime, compiler, and hardware teams to diagnose platform integration and interoperability issues.
- Troubleshoot AI framework compatibility, inference serving configurations, and data center deployments with customers.
What We're Looking For
- At least 3 years of experience in technical support, field application engineering, solutions or customer engineering, or system integration; 7 or more years is preferred.
- Experience with AI infrastructure, inference serving, machine learning deployment, or data center platforms.
- Proficiency with Linux, containers, and distributed systems, plus knowledge of 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 communication skills, including experience supporting OEMs, ODMs, hyperscalers, cloud providers, or enterprise customers.
- Semiconductor, GPU, or AI accelerator industry experience is a plus.
Compensation & Benefits
Base salary starts at $200,000, with stock options. Visa sponsorship policy was not provided.
Location
On-site in the United States.
Compensation
$200K