MLOps Engineer

We are looking for an MLOps Engineer to join our team 🚀

We are building AI products with real-world load — LLMs in production, GPU cluster, agents. We need someone who can keep all of this running.

What you will do: — deploy and maintain LLMs (vLLM, Triton Inference Server) — manage GPU cluster on H200/L4/L40s: resources, VRAM, CUDA MPS — build CI/CD for AI services (GitLab CI) — automate deployment: versioning, rollback, A/B — Kubernetes, Docker — monitor GPU metrics and agent quality (latency p50/p95/p99, throughput, degradation) — work with relational and vector databases

Experience with Alembic and alert setup will be a plus.

If this sounds like you — write to me in private messages or tag those who might be interested 👇