I am adding an AI component to my existing web based company which services lawyers.
I have a basic LLM RAG setup and I need the following done:
Phase 1:
- Update the current file ingestion code
- Optimize chunking strategy for my data set and use case
- Optimize embedding storage and setup for my data set and use case (e.g. what meta-data to add etc.).
Phase 2:
- Optimize PDF parsing
Phase 3:
Ideally this is the same person as 1 and 2 but ok if not. If you can only do 1 and 2 STILL apply.
- Integrate the above with front-end (minimal integration initially as we test with customer)
- Scale the above LLM architecture to support small number of users as part of MVP - You should not overfitted the solution, to support 1m customers.
There will be additional phases beyond this. I am hoping to find someone I can work with longer term
About you:
-You must have deep knowledge with building RAGs (optimizing embedding and chunks). Don't even apply otherwise.
You must be a good communicator.
This job is already closed and no longer accepting applicants, sorry.