Senior AI Platform Engineer (f/m/d) (Full-Time / Part-Time)

AIT Austrian Institute of Technology; Town of Vienna (WI); Hybrid; USD 67,000 - 82,000; Full time

Benefits offered by this job

Health insurance

Paid time off

Retirement plans

Job summary

AI:AT AI FACTORY AUSTRIA in Vienna invites senior software engineers to join the AI Factory Austria supercomputing infrastructure project. You will design and operate scalable LLM inference and fine-tuning services on our on-premise GPU/HPC stack, building an automated B2B AI compute platform.

Requirements include 5-7 years in software/platform engineering, deep Kubernetes experience, Python (Go a plus), ML lifecycle tooling (MLflow/Kubeflow), and eligibility to work in Austria.

Qualifications

• Degree in computer science or a related field, or equivalent professional experience.
• 5-7 years of industry experience in software, platform, or infrastructure engineering, with at least 2 years building ML or AI platforms.
• Deep hands-on experience running Kubernetes in production and building scalable, distributed systems and APIs.
• Hands-on experience with LLM and model serving and inference optimization (e.g. vLLM, Triton).
• Strong programming skills in Python; experience with Go or another backend language is a plus.
• Experience with the ML lifecycle: training and fine-tuning pipelines, experiment tracking, and model registries (e.g. MLflow, Kubeflow).
• Good understanding of GPU workloads, object storage, and Infrastructure as Code, GitOps, and CI/CD practices.
• You are a self-starter, can work independently with limited supervision, and communicate fluently in English.
• You should be eligible for working in Austria.

Responsibilities

• Build and operate scalable LLM inference and fine-tuning services for on-prem GPU/HPC infrastructure.
• Design and run automated B2B AI compute stacks for production workloads.
• Lead model serving, GPU scheduling, and self-service APIs for users.

Skills

Kubernetes

Python

LLM serving

Go or backend

CI/CD

GITOps

GPU workloads

ML lifecycle

Education

Degree in computer science or related field

Tools

Kubernetes

MLflow

Kubeflow

vLLM

Triton

Job description

AI:AT – the AI Factory Austria – is making Austria a hotspot for Artificial Intelligence in Europe.

AI:AT is a joint project of Advanced Computing Austria and AIT. It brings together top-level expertise in high-performance computing, artificial intelligence, and data ecosystems, creating an interdisciplinary innovation environment for research, development, start-ups, and industrial projects.AI:AT – the AI Factory Austria – provides access to cutting-edge AI infrastructure, promotes trustworthy AI and ethical standards, and serves as a hub for networking with national and European partners. The goal is to work with partners from industry and public institutions to develop and implement forward-looking AI technologies and viable AI solutions.

As part of the collaboration within the AI Factory Austria, the Advanced Computing Austria will delegate experts to the AI Factory Austria.To lead AI:AT - comprising several subject matter experts and operational support units - at our location in Vienna (Karl-Farkas Gasse, 1030) we are seeking a:

AI:AT AI FACTORY AUSTRIA

• You will be part of our AI Factory Austria Supercomputing infrastructure project, the largest national and EU project aimed to equip our supercomputers with the hardware and software stack for supporting cutting edge AI workloads.
• You will build one of the most capable and automated B2B AI compute stacks in Austria and Europe, running on our own on-premise GPU and HPC infrastructure.
• You will design and operate scalable LLM inference and fine-tuning services for our users, from model serving and GPU scheduling to self-service APIs.
• Degree in computer science or a related field, or equivalent professional experience
• 5-7 years of industry experience in software, platform, or infrastructure engineering, with at least 2 years building ML or AI platforms
• Deep hands-on experience running Kubernetes in production and building scalable, distributed systems and APIs
• Hands-on experience with LLM and model serving and inference optimization (e.g. vLLM, Triton)
• Strong programming skills in Python; experience with Go or another backend language is a plus
• Experience with the ML lifecycle: training and fine-tuning pipelines, experiment tracking, and model registries (e.g. MLflow, Kubeflow)
• Good understanding of GPU workloads, object storage, and Infrastructure as Code, GitOps, and CI/CD practices
• You are a self-starter, can work independently with limited supervision, and communicate fluently in English
• You should be eligible for working in Austria.

Nice to have:

• Experience with HPC environments and batch schedulers (e.g. SLURM)
• Experience with parameter-efficient fine-tuning and distributed training
• Experience building multi-tenant platforms, including access control and usage metering

What you can expect:

• A flexible schedule with on-site and remote working opportunity
• A supportive and inclusive work environment
• Opportunities for professional growth and development
• The annual gross salary starts at EUR 66.598,-- according to the collective agreement for non-university research. In addition to a competitive salary, we offer a benefits package, including health insurance, paid time off, and retirement plans.
• The position will be awarded for a limited period of time for the current duration of the AI Factory Austria (until June 2028). An extension beyond this period may be possible depending on future project developments.