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

Job summary

The Senior AI Platform Engineer builds and operates an automated AI compute platform on on-premise GPU and high-performance computing infrastructure for AI workloads. The role designs scalable LLM inference and fine-tuning services, including model serving, GPU scheduling, and self-service APIs, and supports production Kubernetes platforms and distributed systems.

Benefits

Qualifications

• 5–7 years of industry experience in software, platform, or infrastructure engineering, including at least 2 years building ML or AI platforms
• Production Kubernetes experience and expertise in scalable distributed systems and APIs
• Hands-on experience with LLM model serving and inference optimization, such as vLLM or Triton
• Strong Python programming skills; Go or another backend language is an advantage
• Experience with ML training and fine-tuning pipelines, experiment tracking, and model registries such as MLflow or Kubeflow
• Understanding of GPU workloads, object storage, Infrastructure as Code, GitOps, and CI/CD
• Ability to work independently with limited supervision
• Fluent English communication
• Eligibility to work in Austria
• HPC and batch scheduler experience, such as SLURM, is an advantage
• Experience with parameter-efficient fine-tuning, distributed training, or multi-tenant platforms is an advantage

Responsibilities

• Build and operate an automated B2B AI compute platform on on-premise GPU and HPC infrastructure
• Design and operate scalable LLM inference and fine-tuning services
• Develop model-serving, GPU-scheduling, and self-service API capabilities

Skills

Degrees

Languages

Work schedule

Industry

Contract length

Relocation