
AI Platform & DevOps Engineer
Rotterdam
Wigi highlights
15+ years, currently working as Senior AI Platform & DevOps Engineer
Built OpenShift operators for FastAPI, SQLAlchemy and Pydantic
Set up on-prem GPU inference with vLLM/SGLang on Kubernetes
The LLM gateway combines OpenAI-compatible APIs for Azure, AWS and own infrastructure, with SSE streaming, per-model routing and rerouting when a provider drops. As the sole engineer, they built and ran the public application end to end, including frontend, backend, database and deployment, using FastAPI, SQLAlchemy, PostgreSQL and Vue on Kubernetes. Development, maintenance and advice on what to build next were also part of the role.
For local LLM work, they set up a self-hosted inference and monitoring stack with vLLM, Prometheus and Grafana, used for testing models and runtime tuning before client deployment. An LLM gateway for routing across Claude, OpenAI-compatible and local models, started as a side project, now forms the base for day-to-day agent work.
Open to offers
Open to new opportunities
Skills
Work experience
Unlocks when they connect with you.
- certifications· 8
- education· 4
Similar available MLOps Engineers
View all- Data & AI Engineer · London, UK · 6 Yrs Exp · Remote · $8,500/mo
- MLOps Engineer (Scaling Machine Learning Workflows) · Sosnowiec, Poland · 7 Yrs Exp · On-site · $4,000/mo
- Senior Terraform ML Infrastructure Engineer | ML Ops · Seattle, WA · 10+ Yrs Exp · On-site · $9,800/mo
- AI Platform Engineer — Kubeflow & Machine Learning · Bydgoszcz, Poland · 10+ Yrs Exp · Hybrid · $3,800/mo
- Staff AI Platform Engineer (Enterprise-Scale Model Deployment) · London, UK · 10+ Yrs Exp · Remote · $6,300/mo