Senior LLM Ops & Evaluations Engineer

DataSnipper; Amsterdam; On-site; EUR 120,000 - 170,000; Full time

Job summary

DataSnipper in Amsterdam is hiring a Senior Software Engineer for LLM Ops & Eval. You will own the LLM gateway, manage multi-provider inference, and ensure reliable, auditable AI workflows at scale.

You’ll build a platform that supports versioned datasets and evaluation runs used by product and ML teams. You will collaborate across engineering to deploy models across clouds, maintain observability, and implement security controls.

Qualifications

• 5+ years in backend or platform engineering with production Python
• Experience building or running LLM inference infrastructure: gateway, multi-provider, failover, cost attribution
• Experience with cloud infrastructure and IaC across Azure and GCP using Terraform
• Experience running a shared service in production: on-call, incidents, postmortems, SLOs
• Hands-on experience with observability tools and dashboards
• Privacy and compliance work: PII handling, anonymisation, retention, access control
• Experience building platform/shared-service capabilities for internal teams

Responsibilities

• Own the LLM gateway: routing, failover, rate limits, retries, cost attribution
• Deploy, version and deprecate models across clouds and regions
• Build the shared evaluation platform: versioned datasets, experiments, run schemas, reporting
• Own infrastructure for async, long-running AI workloads
• Define and maintain integration contracts between platform and teams
• Collaborate with product and ML engineers to deliver self-service platform capabilities

Skills

Backend engineering

LLM inference infra

Cloud IaC (Terraform)

Production on-call & SLOs

Observability (OpenTelemetry, Grafana)

Privacy & compliance

Platform/shared services

Tools

Terraform

OpenTelemetry

Grafana

Job description

DataSnipper in Amsterdam is hiring a Senior Software Engineer for LLM Ops & Eval. You will own the LLM gateway, manage multi-provider inference, and ensure reliable, auditable AI workflows at scale.

You’ll build a platform that supports versioned datasets and evaluation runs used by product and ML teams. You will collaborate across engineering to deploy models across clouds, maintain observability, and implement security controls.