Budget: 15000 UAH Deadline: 7 days
I will raise the servicing infrastructure on Triton Inference Server or BentoML with Docker Compose or K8s manifests, FastAPI or gRPC for inference endpoints and basic monitoring through Prometheus. Assessment of timelines and costs, from 7 days and 15,000 UAH, but I will provide a more accurate estimate after familiarizing myself with the details. The Notion link is only accessible to authorized users, so you can provide public access or describe: what specific models, expected load, what infrastructure already exists?