Staff Machine Learning Engineer, LLM Inference Optimization

What the posting requires

Required

• Python
• vLLM
• Latency
• PyTorch
• SGLang
• Throughput
• TensorRT-LLM
• Quality
• Triton Inference Server
• Utilization

Preferred

• Quantization-aware training
• Distillation
• CUDA
• Post-training quantization
• Speculative decoding
• Triton

These tags are our reading of the posting. They can miss something; the original posting is the reference.