Sergey Tovpeko

Sergey Tovpeko

Platform Engineer · MLOps · AI Infrastructure

Your expert in

Profile

Platform / SRE engineer with deep expertise in automation, observability and infrastructure for ML workloads. Specialized in high-load local model inference (vLLM/Triton), GPU utilization optimization and event-driven RAG systems. Product-minded: I do not only configure infrastructure, but also build internal automation tools, CLI utilities and lightweight client interfaces for monitoring and operating systems end-to-end.

Tech Stack

AI Infrastructure & MLOps

vLLM Ollama CUDA optimization NVIDIA GPU Operator RAG pipelines pgvector Qdrant n8n

Platform & DevOps

Kubernetes (k3s) Docker GitLab CI Automated Delivery Pipelines Ansible Linux eBPF

Backend & Observability

Python (FastAPI) Go C# PostgreSQL ClickHouse Apache Airflow Prometheus Grafana VictoriaMetrics ELK Stack MinIO/S3

Internal Tooling & Client Interfaces

Kotlin (Jetpack Compose) Flutter (Dart) REST/WebSocket clients CLI utilities

Services

AI Infrastructure & Inference Serving Local high-load LLM inference with vLLM/Ollama, GPU observability and production-grade operations. Details

I design production-like inference environments for local models: containerization, CUDA/GPU monitoring, autoscaling, latency/throughput metrics and cost-aware operations.

MLOps and RAG Platforms RAG pipelines, vector search, agent workflows and model delivery into Kubernetes. Details

I build event-driven AI pipelines with FastAPI, n8n, Supabase and pgvector/Qdrant: indexing, retrieval, orchestration, quality signals and repeatable deployments.

Platform Engineering & DevOps Kubernetes/k3s, Docker, GitLab CI, Ansible, Linux and reproducible delivery pipelines. Details

I build internal platforms for teams: dev/prod environments, IaC automation, GitLab CI, release flows, containerization, secrets and operational runbooks.

Observability and Data Platforms Prometheus, Grafana, VictoriaMetrics, ClickHouse, ELK, Airflow, PostgreSQL and MinIO/S3. Details

I implement metrics, logs, alerts and long-term storage, design data pipelines and reduce MTTR through clear dashboards and operational signals.

End-to-End Internal Tooling CLI utilities, dashboards and lightweight client interfaces for complex platforms. Details

I close tasks end-to-end: from backend/API and automation to internal Kotlin/Flutter/Web tools for diagnostics, telemetry and system management.