AI LLM & Infrastructure Engineer - Hybrid, Flexible Hours

Esyen; Avezzano; On-site; EUR 30,000 - 37,000; Full time

Benefits offered by this job

Health coverage

Professional development

Team-building activities

Welfare benefits

Flexible working hours

Growth opportunities

Job summary

ESYEN is seeking an AI LLM & Infrastructure Engineer to design, deploy and operate AI infrastructure for LLM and agentic applications. You will ensure GPUs, storage, networking, and orchestration support high-performance AI workloads across cloud and on‑prem environments.

You will collaborate with AI, Software Engineering, and R&D teams to optimise inference architectures and infrastructure costs while improving reliability and scalability.

Qualifications

• Degree in CS/Engineering or related field is an advantage.
• Professional experience in AI infrastructure, system administration, cloud infra, or software engineering is preferred.

Responsibilities

• Design and manage GPU infrastructure for AI/LLM workloads.
• Configure and maintain multi-GPU servers.
• Deploy and manage open-source LLMs.
• Monitor GPU, memory, and compute resources.
• Support cloud, on-premise, and hybrid environments.
• Configure inference servers using vLLM, SGLang, or TGI.

Skills

Linux

Docker

Kubernetes

NVIDIA GPU

TCP/IP

Linux networking

Storage

Python

Bash scripting

Git

CI/CD

REST APIs

Monitoring

LLM Inference

vLLM

SGLang

TGI

Education

Bachelor's degree in Computer Science, Computer Engineering, Electronic Engineering, Telecommunications, or related field

Tools

Docker

Kubernetes

NVIDIA GPU tooling

Git

CI/CD pipelines

Job description

ESYEN is seeking an AI LLM & Infrastructure Engineer to design, deploy and operate AI infrastructure for LLM and agentic applications. You will ensure GPUs, storage, networking, and orchestration support high-performance AI workloads across cloud and on‑prem environments.

You will collaborate with AI, Software Engineering, and R&D teams to optimise inference architectures and infrastructure costs while improving reliability and scalability.