Systems & Platform Engineer focused on observability, automation, and AI infrastructure.
Gözlemlenebilirlik, otomasyon ve AI altyapısı üzerine çalışan sistem mühendisiyim.
- Standing up on-prem LLM serving infrastructure with vLLM + LiteLLM as API gateway
- Building a unified observability stack (Prometheus, Grafana, Zabbix, ELK) across heterogeneous infrastructure
- Driving infrastructure-as-code & automation with Ansible, moving toward AWX and Kubernetes-native workflows
- Writing about what I build — turning internal work into public, reproducible knowledge
Observability: Prometheus · Grafana · Zabbix · ELK
Automation & Scripting: Ansible · Python
Containers: Docker
Platforms: Linux · VMware · Storage (IBM Storwize V7000, HPE Primera) · Active Directory · Exchange
- AWX — moving Ansible workflows from CLI to centralized orchestration
- Kubernetes — preparing for CKA, hands-on with cluster operations
- vLLM + LiteLLM — on-prem LLM serving and API gateway patterns
- CKA — Certified Kubernetes Administrator
- AZ-104 — Azure Administrator
- Terraform — Infrastructure as Code
9 years in IT infrastructure. Started in geospatial systems (GIS) — 7 years working with spatial data, mapping platforms, and large-scale geographic datasets — then transitioned into systems administration and platform engineering, where the discipline of handling structured, high-volume data carried over naturally.
The GIS years taught me how to think about data at scale before I ever touched a Prometheus query. Now I apply that to infrastructure.
- LinkedIn: bugrazen
"The institution pays the salary. The proof builds the career."