🚀 DevOps / Cloud / AI Infra 🧠 Team Lead @ Gcore Cloud 📍 Nicosia, Cyprus

Aleks

Making infra boring again. In a good way. Kubernetes, RDMA/InfiniBand, H100, Grafana, vLLM, GPU-aware scheduling. Simple architectures, strict SLOs, zero drama.

Email me ↗ GitHub LinkedIn

⚙️ What I do

I build and tame cloud infrastructure. K8s, networking, storage, observability, pipelines. I make it fast and painless for engineers.

🧩 What I tinker with

AI infra: training/inference, LoRA/SFT, vector DBs, vLLM. I love optimizing the GPU stack, NUMA, RDMA.

📈 KPI, but humane

99.95% SLO TTR ↓ x2 Cost ↓ 20–40% Deploys ↑ daily
Infra without tears

Clean interfaces. Predictable releases. Sensible alerts. Documentation people actually read.

🛠 Technologies

Kubernetes, Cilium, Helm, External Secrets, Terraform, ArgoCD, Prometheus/Grafana/VictoriaMetrics, Nix, GitHub/GitLab CI, KubeVirt, SR-IOV, IB/RDMA, NV GPU (H100), MLflow, vLLM.

💬 Talks / threads

About Kubernetes networking, admission policies, observability, AI infra.

🚧 Projects / Threads

🔥 AptenBot

Telegram proxy-bot for LLM providers. Minimal, stylish, vibey.

Try

🐟 Tshawytscha AI

Friendly AI assistant. React + FastAPI, self-hosted, open source.

Try

📨 Telegram

A collection of posts about K8s, Observability, and AI infra.

Telegram