A worldwide audience needs p99 ≤ 85 ms at 8,000 rps, 99.95% availability, critical durability — under $1,500/mo. You've inherited only a single-region app fleet and a database: no edge caching, no in-memory cache, single-AZ, on-demand.
You have to build the rest yourself from the component palette — but not everything there belongs. Distant users can only be served fast by going multi-region (set the deployment footprint) and adding a CDN for edge caching; an in-memory cache keeps the database in range. A Global Accelerator looks tempting for latency, but it's costly and redundant once you have a CDN and multi-region — adding it just burns the budget.