L

Lyceum

European sovereign GPU cloud for AI workloads

Member of Technical Staff - AI Inference platform

Site Reliability EngineeringConfirmed live in the last 24 hours
Full-timeZürich, SwitzerlandNo salary listedIn-person

About the Job

Requirements

  • At least 3 years of experience in backend, infrastructure, or systems engineering.
  • Strong proficiency in Go and Python.
  • Experience building or operating a model-serving platform or machine-learning platform.
  • A solid understanding of systems performance, including profiling, benchmarking, and optimizing latency and throughput.
  • Familiarity with observability tooling such as Prometheus, Grafana, or OpenTelemetry.
  • Understanding of security fundamentals, including network isolation, authentication, encryption, and multi-tenancy.

Responsibilities

  • Architect and implement systems that enable the inference platform to scale to thousands of concurrent users, including request routing, load balancing, autoscaling, and resource scheduling across GPU clusters.
  • Build monitoring, alerting, and incident-response tooling; design for graceful degradation, automatic recovery, and minimal downtime.
  • Profile and optimize the full inference path from request ingestion through model execution to response delivery, identifying and eliminating bottlenecks at every layer.
  • Evaluate and integrate open-source inference frameworks and tooling, such as Dynamo, vLLM, and Triton, where they improve serving-stack throughput, latency, or stability.

Desired Qualifications

  • Experience with NVIDIA Dynamo or similar inference orchestration or routing frameworks.
  • Hands-on experience with GPU serving infrastructure such as vLLM, Triton, or TensorRT-LLM.
  • Experience with Kubernetes in a production environment, including deployment, networking, and resource management.
  • Experience operating at scale, including 10,000+ requests per second, multi-region, or multi-cluster environments.
  • Comfort working on-call or in incident response when issues occur.

About the Company

Lyceum

European sovereign GPU cloud for AI workloads

Lyceum builds a sovereign GPU cloud platform that makes high-performance computing for AI workload easy and local to Europe. It operates a software layer that abstracts infrastructure so users can deploy AI models with a single click from their IDE. The platform automates hardware selection, offers upfront transparent pricing, and schedules elastic workloads to prevent overprovisioning and reduce DevOps costs. Lyceum runs its own European data-center hardware, including a liquid-cooled facility in Paris, ensuring data sovereignty and residency for customers, with NVIDIA Blackwell B200 GPUs deployed early. This positions Lyceum as a European alternative to US-based hyperscalers. Its goal is to broaden access to powerful AI compute in Europe by expanding its engineering and commercial teams, securing hardware partnerships, and building more data centers to maintain control over performance, cost, and data governance.

Company size
11-50
Company stage
Seed
Total funding
$11.3M
Headquarters
Zurich, Switzerland
Founded
2025

Recently Posted Jobs

Explore more opportunities at Lyceum

See more jobs