Senior AI Platform Engineer — On-Prem GPU/LLM Infra
Posted Updated
Who recruits here Pro
Up to three recruiters at AIT Austrian Institute of Technology GmbH with their work email, so you can write to a person.
Part of Pro. How it works
Description
AI:AT – the AI Factory Austria – is seeking a seasoned engineer to lead its Vienna-based AI infrastructure initiative. You will help build automated B2B AI compute stacks on on-premise GPU and HPC systems, and design scalable LLM inference and fine-tuning services for users.
The role requires 5-7 years in software/platform engineering with hands-on Kubernetes, ML lifecycle know-how, and strong Python (Go a plus). English fluency and Austrian work eligibility are essential.
Lead AI:AT - Vienna-based team and AI Factory Austria projects. Build automated B2B AI compute stacks on on-premise GPU and HPC infrastructure. Design and operate scalable LLM inference and fine-tuning services from model serving to APIs. Degree in computer science or 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; 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. Health insurance Retirement plans Flexible schedule Remote work option On-site and remote workingSkills
Sign in to read and join the discussion.