Senior AI Platform Engineer

Permanent
100%
Zurich (Hybrid)
Internal
April 23, 2026

Architect and scale our sovereign GPU-accelerated AI platform on Exoscale SKS. Build the reliable, high-performance infrastructure that powers production-grade autonomous agents for Swiss and European enterprises.

About the Role

We are seeking a Senior AI Platform Engineer to take ownership of the foundational infrastructure thatpowers Singularity IO’s sovereign Agentic AI Platform. You will design, build, and optimize the GPU-accelerated runtimeenvironment that enables reliable, compliant, and high-performance autonomous agents at scale.This is a hands-on platform role where your work directly impacts every agent deployed for our clients and our internal digitalworkforce.

Key Responsibilities

• Design and maintain the core sovereign platform running on Exoscale SKS GPU clusters  

• Optimize Ollama inference, model serving, and vector store performance (Qdrant)  

• Build robust Kubernetes-based deployment pipelines and observability systems  

• Implement cost-efficient GPU resource scheduling and auto-scaling strategies  

• Ensure full EU AI Act and DSG/GDPR compliance across the entire platform layer  

• Collaborate with Agentic AI Engineers to enable seamless transition from Dify low-code to LangGraph production workflows

Required Skills & Qualifications

• 5+ years of experience in AI/ML platform engineering or MLOps  

• Strong expertise with Kubernetes, GPU acceleration, and high-performance inference  

• Hands-on experience with Ollama, vector databases (Qdrant), and containerized LLM serving  

• Proficiency in Python, Terraform, and infrastructure-as-code practices  

• Deep understanding of cloud cost optimization and performance tuning at scale  

• Experience in regulated environments (EU AI Act / GDPR) is a strong advantage

RAG Architecture
Python

Our Technology Stack

You will be working with a modern, sovereign-first technology stack designed for scale and security.

Exoscale SKS
Ollama
Qdrant
Kubernetes
NVIDIA GPU Operator
LangGraph
Dify
n8n

What Success Looks Like

• Within 30 days: You will have optimized our core inference pipeline and established new monitoring standards.

• Within 90 days: You will have implemented GPU resource scheduling that improves cost-efficiency by at least 25%.

• Within 6 months: You will be the go-to expert for platform reliability and will have contributed to major upgrades thataccelerate agent deployment speed across the company.

Ready to build the future of sovereign AI?

Join Singularity and help us engineer production-grade, compliant AI solutions with Swiss precision.

Questions? Reach out to our talent team.