Seeking Guidance on Implementing LLM and Generative AI in a New Role.

Hi everyone,

I recently got a job that involves implementing LLM and Generative AI. During the interview, we discussed topics like Reinforcement Learning, Deep Learning, and Machine Learning. I’m finishing my MSc in Computer Science, where I’ve worked on projects involving simple Deep Learning implementations (data extraction, cleaning some MLP).

Essentially, I will have access to servers for computing and a laptop, and I’ll be the sole programmer responsible for establishing and demonstrating value.

I am looking for resources and maybe some examples of how to do that so far I have recommended:

• Hugging Face - Documentation

• Intro to Large Language Models by Andrej Karpathy

I also plan to attend local meetups about LLM and PyTorch.

I’m looking for practical advice on learning these technologies while developing them, particularly regarding development workflows, cloud backups, and coding standards, as I will be working independently.

I know if I can achieve something easier and faster with a simple Machine Learning model I will do that.

Any help would be greatly appreciated.