AI Platform Engineer (OneAI)

Role overview This role focuses on building out an AI infrastructure platform designed to run high-performance inference and training workloads across diverse cloud and edge environments. The position sits at the intersection of applied AI, systems engineering, and product design, contributing to a strategic AI initiative within an established open-source cloud management ecosystem. The work shapes both the technical backbone and the user-facing experience of a platform intended to serve enterprise customers managing the full model lifecycle.

Responsibilities - Design, implement, and deploy advanced AI capabilities within an inference and training platform built on top of an open-source cloud management system - Integrate AI frameworks and engines such as vLLM, PyTorch, and Unsloth into a secure, scalable, and observable platform supporting compute provisioning, workload scheduling, and reliable APIs for serving and fine-tuning - Shape user-facing workflows for managing models, configuring deployments, and operating inference and training jobs - Connect the system with public model repositories like Hugging Face to streamline model and dataset discovery, import, versioning, and deployment - Optimize performance and cost efficiency, implement GPU-aware operations, and establish deployment strategies that scale efficiently

Requirements - Hands-on experience with AI/ML frameworks such as PyTorch and inference engines such as vLLM, plus familiarity with tools like Unsloth - Background in cloud infrastructure, systems engineering, or platform engineering, with knowledge of GPU-aware operations and workload scheduling - Ability to design scalable, observable systems with reliable API exposure across the full model lifecycle - Comfort working across both backend infrastructure and product or user-experience design - Experience integrating with model and dataset repositories and operating model versioning pipelines

Benefits and work setup - Fully remote, distributed, international team with flexible hiring options including full-time or part-time arrangements and employment or contractor structures depending on location - Customized workstation with choice of operating system - Private health insurance plus flexible remuneration covering meals, transport, and nursery or childcare - Paid time off for holidays, personal time, sick time, and parental leave, plus Friday afternoons off year-round and reduced summer hours - Twice-yearly company-wide in-person all-hands meetings, with some onboarding and project work requiring travel within Europe - Engineering-first culture that encourages exploring new technologies, supports digital disconnecting, and promotes a healthy work-life balance