To optimize read performance on BigQuery tables via Airbyte, you can use a data transformation tool like dbt. Airbyte has a native integration with dbt that you can use to run transformations on your data. Here's a general process you can follow: 1. Import the existing generated DBT models for your connection. 2. Tweak these models as per your requirements. 3. Declare it as a custom transformation. You can find a guide on how to do this in the [Airbyte documentation](https://docs.airbyte.com/operator-guides/transformation-and-normalization/transformations-with-dbt). Please note that optimizing read performance often involves creating new models or optimizing existing ones based on your specific use case. This could involve creating aggregated tables, optimizing joins, or creating indexes, among other things. Remember, the goal is to structure your data in a way that makes your most common queries as fast as possible. This often involves a trade-off between storage cost and query performance. If you find a way to optimize the auto-generated SQL script, you can also contribute to the Airbyte community by opening a PR on their repo. This was suggested in a [forum post](https://discuss.airbyte.io/t/1515) on the Airbyte community forum.