AI LLM & Infrastructure Engineer

Esyen; Avezzano; On-site; EUR 22,000 - 37,000; Full time

Benefits offered by this job

Health coverage

Professional development

Team building

Welfare benefits

Flexible hours

Career growth

Job summary

ESYEN seeks an AI LLM & Infrastructure Engineer to design, deploy and operate AI infrastructure supporting LLM and RAG workloads. You will work with AI, software engineering and R&D teams to optimise multi-GPU, storage and networking for cloud, on-premise and hybrid environments.

The role focuses on GPU infra, LLM deployment and scalable infrastructure, with emphasis on modern open-source tools and observability in a fast-paced R&D setting.

Qualifications

• Experience with AI infrastructure, system administration or cloud infra.
• Hands-on Linux, Docker and Kubernetes experience.
• Familiarity with GPU infrastructure and AI/LLM tech.

Responsibilities

• Design and operate GPU infrastructure for AI/LLM workloads.
• Deploy and manage open-source LLMs and inference servers.
• Configure multi-GPU servers and storage for AI workloads.
• Monitor performance, troubleshoot bottlenecks and ensure reliability.

Skills

Linux

Docker

Kubernetes

NVIDIA GPU

TCP/IP networking

Storage (local & distributed)

Python

Bash scripting

Git & CI/CD

REST APIs

Monitoring & observability

LLM inference architectures

vLLM / SGLang / HuggingFace TGI

Education

CS/CE/EE/Telecom degree (advantage)

Job description

Are you an AI LLM & Infrastructure Engineer looking for an opportunity to work on innovative Artificial Intelligence and Large Language Model technologies?

Would you like to contribute to the design, deployment, and management of AI infrastructure, working in an environment where GPU, cloud, on‑premise, and distributed systems play a key role?

We are looking for an AI LLM & Infrastructure Engineer to join our team, supporting the development and operation of the infrastructure required for AI, LLM, RAG, and agentic applications.

You will work on the design, deployment, maintenance, and optimisation of AI infrastructure, collaborating closely with AI, Software Engineering, and R&D teams.

ABOUT US

ESYEN is an engineering company offering services to the Space Industry, working with major international Customers and Agencies such as EUSPA and ESA. Since 2012, we have played an active role in major European Space Programmes, including Earth Observation, Navigation and Secure Satcom.

Our team has a solid track record in providing Ground Segment services across major European Space Programmes. ESYEN operates in Italy, Germany, France and Spain, with a strong commitment to innovation and quality of service.

WORK LOCATION

Avezzano (AQ)

WHAT WE LOOK FOR

Education & Experience

A degree in Computer Science, Computer Engineering, Electronic Engineering, Telecommunications, or a related field is considered an advantage.

Professional experience in AI infrastructure, system administration, cloud infrastructure, or software engineering is preferred.

Technical Skills

• Experience with Linux, Docker and Kubernetes
• Hands‑on experience with NVIDIA GPU infrastructure
• Knowledge of TCP/IP and Linux networking
• Experience with local, distributed, and object storage
• Knowledge of Python and Bash scripting
• Experience with Git and CI/CD
• Experience with REST APIs and service deployment
• Knowledge of monitoring and observability
• Good understanding of LLM inference architectures

Experience with vLLM, SGLang, Hugging Face TGI, or equivalent technologies is considered a strong advantage.

Soft Skills

• Strong engineering and problem‑solving approach
• Proactive and structured attitude
• Ability to work across software and infrastructure activities
• Strong attention to detail
• Good communication and teamwork skills
• Ability to work effectively in an R&D environment

WHAT YOU WILL DO

As an AI LLM & Infrastructure Engineer, you will contribute to the design and operation of the infrastructure supporting AI and LLM applications.

AI Infrastructure Management

• Design and manage GPU infrastructure for AI/LLM workloads
• Configure and maintain multi‑GPU servers
• Manage GPU, VRAM, storage, and computing resources
• Support cloud, on‑premise, and hybrid environments

LLM Deployment & Optimisation

• Deploy and manage open‑source LLMs
• Configure inference servers using vLLM, SGLang, TGI, or equivalent technologies
• Optimise inference performance, latency, throughput, and resource utilisation
• Support model quantisation and multi‑GPU inference activities

Kubernetes & Infrastructure

• Deploy AI workloads using Docker and Kubernetes
• Support autoscaling, scheduling, and workload management
• Configure networking and storage required by AI workloads
• Contribute to distributed and multi‑node GPU environments

Monitoring & Troubleshooting

• Monitor GPU, memory, inference performance, and system resources
• Implement logging, monitoring, and observability
• Investigate infrastructure bottlenecks and performance issues
• Contribute to improving reliability, scalability, and infrastructure costs

BENEFITS

The successful candidate will be offered a full‑time contract, with a competitive salary package reflecting skills and experience and aligned with the company’s salary scale.

Additional benefits include:

• Health coverage as outlined by the applicable national contract
• Access to professional development and training opportunities
• Team‑building and extracurricular activities
• Enhanced annual welfare benefits
• Flexible working hours, where compatible with project requirements
• Opportunities for professional growth

Salary range: € 30.000 – € 37.000, depending on relevant experience and qualifications.