Not sure about the LLM part. I still prefer my transformation to be done by LLVM, in many cases rigorously proven to be correct instead of hopefully not hallucinating.
We're not translating Python directly to LLVM IR (I think I've seen other projects do this). We translate Python to C++/Rust first, where we have rigorous unit tests for every operation we support translating. We then use LLVM for downstream compilation to object code.
Here's some more context: https://docs.fxn.ai/predictors/compiler