AI Inference SRE - High-Performance Serving

F5 is seeking an AI Inference Engineer to bridge high performance model development and deployment. You will optimize Large Language Models for diverse environments-from data centers to edge devices-focusing on throughput, latency, and accuracy.

Collaborate with hardware teams on GPU and AI accelerator utilization and build scalable inference architectures. The role emphasizes real time and batch inference orchestration with Kubernetes, advanced tooling like vLLM, TensorRT, Triton, and strong