AI Inference SRE: High-Throughput, Low-Latency

F5 Networks, Inc.; Dublin; Hybrid; EUR 90,000 - 170,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

F5 Networks, Inc. is seeking an AI Inference Engineer to bridge high‑performance model development and optimized deployment environments. The role focuses on optimizing Large Language Models for inference across GPUs, edge devices, and data centers, emphasizing throughput, latency, and accuracy.

The successful candidate will design scalable infrastructure, leverage hardware acceleration, and work with Kubernetes for online and batch inference, ensuring enterprise‑grade reliability.

Qualifications

• Strong background in high‑performance AI workflows.
• Experience with LLMs and inference optimization.
• Familiarity with Docker, Kubernetes and cloud platforms (AWS/GCP/Azure).

Responsibilities

• Build and optimize high‑performance AI inference engines (vLLM, TGI, TensorRT) at scale.
• Deliver low-latency inference solutions across multiple apps via deployment optimizations.
• Profile and optimize models for GPUs/TPUs/Apple Silicon; collaborate with hardware teams.
• Design auto‑scaling for online and batch inference using Kubernetes for routing.
• Establish observability for TTFT, tokens/second, memory bandwidth; run load tests.

Skills

Python

C++

Rust

Golang

Tools

vLLM

TensorRT

Llama.cpp

Ollama

Docker

Kubernetes

AWS/GCP/Azure

Job description

F5 Networks, Inc. is seeking an AI Inference Engineer to bridge high‑performance model development and optimized deployment environments. The role focuses on optimizing Large Language Models for inference across GPUs, edge devices, and data centers, emphasizing throughput, latency, and accuracy.

The successful candidate will design scalable infrastructure, leverage hardware acceleration, and work with Kubernetes for online and batch inference, ensuring enterprise‑grade reliability.