DevOps Engineer for AI FastAPI Deployment

We are looking for an experienced DevOps / Backend Engineer to properly deploy and configure our existing AI-based Python FastAPI application on a Google Cloud Compute Engine GPU server. The application is already developed, and the GPU VM has already been created/configured in Google Cloud Console. We need someone to complete the production deployment and correctly configure all related infrastructure. Tech Stack Python FastAPI OpenCV AI / ML models NVIDIA GPU Google Cloud Platform / Compute Engine Vultr Object Storage (S3-compatible) Linux Nginx Domain / DNS / SSL Main Tasks Deploy our existing FastAPI application to the Google Cloud GPU VM Verify and correctly configure NVIDIA drivers / CUDA Verify that the Python AI application is actually using the GPU Install and configure all required Python/OpenCV dependencies Configure FastAPI for production Configure Uvicorn / Gunicorn or another appropriate production setup Configure Nginx as a reverse proxy Connect our domain to the Google Cloud server Configure HTTPS / SSL certificate Configure firewall and required ports Configure environment variables and secrets Configure the application as a systemd service or another reliable process manager Make sure the API automatically starts after server reboot Configure logs and basic monitoring Vultr Object Storage We also use Vultr Object Storage, which provides an S3-compatible API. The developer should: Configure the Vultr S3 bucket correctly Configure bucket credentials and permissions Connect the Python/FastAPI application to Vultr Object Storage Configure uploads/downloads from the application Verify that files are correctly stored and retrieved Make sure credentials are stored securely Expected Result At the end of the job we should have a production-ready setup where: Domain → HTTPS/Nginx → FastAPI → AI/OpenCV → NVIDIA GPU and FastAPI → Vultr S3 Object Storage The application should: Be accessible through our domain Use HTTPS Run reliably in production Correctly use the NVIDIA GPU Correctly communicate with Vultr S3 storage Automatically restart after crashes/reboots Have proper logging Have a clean and documented deployment configuration Required Experience Strong experience with: Google Cloud Platform (GCP) Google Compute Engine NVIDIA GPU servers CUDA Python FastAPI OpenCV Nginx Uvicorn / Gunicorn Linux systemd S3-compatible Object Storage DNS / Domain configuration SSL / Let's Encrypt Experience deploying AI/ML applications on Google Cloud GPU instances is highly preferred. The application itself is already developed. We mainly need an experienced engineer to properly configure and deploy the infrastructure and application for production. Please include examples of similar FastAPI + GPU / AI / GCP deployments you have worked on.