AI Inference Engineer — High-Performance, Low-Latency ML

F5; Dublin; On-site; EUR 90,000 - 150,000; Full time

Job summary

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

Responsibilities include building inference engines with vLLM, TensorRT, and Triton, profiling models for CUDA/TensorRT, CoreML, and AI accelerators, and designing scalable pipelines with Kubernetes.

Qualifications

• Proficiency in Python, C++, Rust or Golang for high‑performance AI workflows.
• Hands‑on experience with inference tools like vLLM, TensorRT, Llama.cpp, Ollama.
• Familiar with infrastructure: Docker, Kubernetes, cloud platforms (AWS, GCP, Azure).
• Knowledge of GPU/TPU hardware optimization and profiling techniques.

Responsibilities

• Build and maintain high‑performance AI serving engines for diverse deployments.
• Profile and optimize models for GPUs, Apple Silicon, and AI accelerators.
• Design auto‑scaling inference pipelines using Kubernetes and efficient routing.
• Establish observability for TTFT, tokens/second, and memory bandwidth, with load testing.

Skills

Python

C++

Rust

Golang

Tools

vLLM

TensorRT

Llama.cpp

Ollama

Docker

Kubernetes

Job description

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

Responsibilities include building inference engines with vLLM, TensorRT, and Triton, profiling models for CUDA/TensorRT, CoreML, and AI accelerators, and designing scalable pipelines with Kubernetes.