Platform Engineer — Scalable AI Inference

Startupvalleys; Zürich; On-site; CHF 120,000 - 180,000; Full time

Job summary

Startupvalleys is seeking a backend/infrastructure engineer to build a scalable, secure AI inference platform in Zürich. You will own reliability, performance, and scalability, ensuring the system handles thousands of concurrent users with minimal downtime.

You will drive observability, incident response, and throughput optimization, while evaluating open-source inference frameworks and GPU serving tooling to evolve the serving stack.

Qualifications

• ,

Responsibilities

• Design and implement scalable backend/infrastructure for an AI inference platform.
• Ensure reliability, graceful degradation, and automated recovery under heavy load.
• Profile, benchmark, and optimize latency and throughput across the stack.
• Integrate open-source inference frameworks and tooling to improve throughput, latency, or stability.

Skills

Go

Python

Model serving

Observability

Security

Kubernetes

System profiling

Tools

Prometheus

Grafana

OpenTelemetry

Job description

Startupvalleys is seeking a backend/infrastructure engineer to build a scalable, secure AI inference platform in Zürich. You will own reliability, performance, and scalability, ensuring the system handles thousands of concurrent users with minimal downtime.

You will drive observability, incident response, and throughput optimization, while evaluating open-source inference frameworks and GPU serving tooling to evolve the serving stack.