Senior AI Inference Platform Engineer

Lyceum; Zürich; On-site; CHF 120,000 - 200,000; Full time

Job summary

Lyceum is seeking a Member of Technical Staff to own and operate its AI inference platform. You will architect a reliable, secure, and scalable serving stack that can handle thousands of concurrent users while evolving the platform as we grow.

Your focus includes scalable routing, autoscaling across GPU clusters, robust observability, and performance optimization from ingestion to model execution. You will join a world-class team and help maintain security, multi-tenancy, and high availability.

Qualifications

• 3+ years of backend, infrastructure, or systems engineering experience.
• Strong proficiency in Go and Python.
• Experience building or operating a model serving platform or ML platform.
• Solid understanding of systems performance - profiling, benchmarking, and optimising latency and throughput.
• Familiarity with observability tooling (Prometheus, Grafana, OpenTelemetry, or similar).
• Understanding of security fundamentals - network isolation, authentication, encryption, multi-tenancy.

Responsibilities

• Design and implement scalable routing, load balancing, and autoscaling across GPU clusters.
• Build robust monitoring, alerting, and incident response tooling to reduce downtime.
• Profile and optimise the full inference path from request to response to reduce latency and improve throughput.
• Evaluate open-source inference frameworks and tooling to improve throughput and stability.
• Ensure security and multi-tenancy considerations are integrated into the serving stack.

Skills

Go

Python

Model serving platform

Performance profiling

Observability tooling

Security fundamentals

Tools

Prometheus

Grafana

OpenTelemetry

Kubernetes

NVIDIA Dynamo

vLLM

Triton

Job description

Lyceum is seeking a Member of Technical Staff to own and operate its AI inference platform. You will architect a reliable, secure, and scalable serving stack that can handle thousands of concurrent users while evolving the platform as we grow.

Your focus includes scalable routing, autoscaling across GPU clusters, robust observability, and performance optimization from ingestion to model execution. You will join a world-class team and help maintain security, multi-tenancy, and high availability.