Note: The job is a remote job and is open to candidates in USA. The company is a well-funded AI infrastructure company building a next-generation platform for production LLM inference. The Customer Facing Engineer will help enterprise customers deploy, optimize, and troubleshoot LLM inference workloads, focusing on inference performance, GPU optimization, runtime expertise, and customer adoption.

Responsibilities

• Work directly with enterprise customers on LLM inference deployments
• Optimize inference performance (latency, throughput, GPU utilization)
• Troubleshoot runtime issues across model, GPU, and infrastructure layers
• Support customer adoption of modern inference stacks
• Collaborate with product + engineering to improve inference tooling

Skills

• Strong experience with LLM inference in production
• Hands‑on expertise with at least one:
• VLLM
• SGLang
• TensorRT‑LLM
• Triton
• PyTorch Dynamo
• GPU inference deployments
• Model bring‑up
• Solid Python engineering skills
• Experience working directly with customers or external engineering teams
• Ability to debug complex ML systems end‑to‑end

Company Overview