Staff Observability Engineer — GPU Infra

Lyceum

Zürich

On-site

CHF 120,000 - 190,000

Full time

41 hours ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Lyceum is seeking an experienced site reliability/observability engineer to build the monitoring stack across GPUs, Kubernetes, and inference workers. You will define metrics, logs and traces pipelines, ensure fast alerting, and provide on-call readiness to anticipate incidents.

You will collaborate with engineers to improve SLOs, reduce alert noise, and deliver clear customer-facing visibility into usage and health of Lyceum's platform.

Qualifications

  • 3+ years of site reliability, observability or infrastructure engineering experience.
  • Production experience with Grafana, Prometheus, OpenTelemetry or similar tooling.
  • Strong proficiency in Go and Python, with solid Linux and Kubernetes fundamentals.

Responsibilities

  • Build and run the observability stack across data centres, ensuring fast metrics, logs and traces pipelines.
  • Define SLOs with product teams and create precise alerts for on-call and incident response.
  • Proactively detect issues by analysing system and workload patterns and turning incidents into automated checks.
  • Provide customer-facing visibility into usage, performance and health of Lyceum’s platform.

Skills

Go
Python
Linux
Networking
Kubernetes

Tools

Grafana
Prometheus
OpenTelemetry

Job description

Lyceum is seeking an experienced site reliability/observability engineer to build the monitoring stack across GPUs, Kubernetes, and inference workers. You will define metrics, logs and traces pipelines, ensure fast alerting, and provide on-call readiness to anticipate incidents.

You will collaborate with engineers to improve SLOs, reduce alert noise, and deliver clear customer-facing visibility into usage and health of Lyceum's platform.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Member of Technical Staff – Monitoring
Member of Technical Staff – Monitoring

Lyceum • Zürich

On-site
CHF 120,000 - 190,000
GPU Infra Platform Engineer: Provisioning, Isolation & Uptime
GPU Infra Platform Engineer: Provisioning, Isolation & Uptime

Lyceum • Zürich

On-site
CHF 120,000 - 170,000
Infra Engineer: AI Inference & Kubernetes
Infra Engineer: AI Inference & Kubernetes

Lyceum • Zürich

On-site
CHF 150,000 - 190,000
GPU Platform Engineer
GPU Platform Engineer

Lyceum • Zürich

On-site
CHF 120,000 - 180,000
Member of Technical Staff – Isolation, Provisioning, Uptime, Monitoring
Member of Technical Staff – Isolation, Provisioning, Uptime, Monitoring

Lyceum • Zürich

On-site
CHF 120,000 - 170,000
Member of Technical Staff – AI Inference platform, robustness
Member of Technical Staff – AI Inference platform, robustness

Lyceum • Zürich

On-site
CHF 120,000 - 200,000
Staff Engineer, GPU VM Platform & Infra
Staff Engineer, GPU VM Platform & Infra

Lyceum • Zürich

On-site
CHF 120,000 - 170,000
Staff Systems Engineer — VM Infra & GPU Platform
Staff Systems Engineer — VM Infra & GPU Platform

Techeurope • Zürich

On-site
CHF 110,000 - 170,000
Outstanding team
Early-stage company
Ownership of GPU compute access
Senior AI Inference Platform Engineer
Senior AI Inference Platform Engineer

Lyceum • Zürich

On-site
CHF 120,000 - 200,000
Platform Security Engineer — Sovereign Cloud & GPU Infra
Platform Security Engineer — Sovereign Cloud & GPU Infra

Lyceum • Zürich

On-site
CHF 120,000 - 180,000
Top locations