We’re developing a SaaS generative AI application built on top of Google Vertex Gemini. Our service serves steady, ongoing inference requests and requires consistent, reliable model capacity to keep our service running smoothly.
We’re looking for technical partners who have unused Vertex AI quota on Google Cloud. Google for Startups quota is welcome. We prefer larger capacity pools to match our continuous workload demands.
We have our own isolated backend & proxy stack for integration testing. We can spin up a validation test quickly to confirm the connection and model performance.
If you’re open to long-term capacity collaboration for an AI SaaS project, send me a DM to discuss further.
Thanks!