SkillData ScientistAI/ML EngineerForward Deployed Engineer
Library · concept
LLMs and NLP
Work with text, from classic NLP to large language models. Call LLM APIs reliably, get structured output, and choose between prompting, retrieval and fine-tuning.
LLMs and generative AI appeared in 62% of the AI/ML Engineer and 75% of the Forward Deployed Engineer job descriptions we read. Classic NLP still matters: many text problems are solved faster and cheaper without an LLM.
Examples use the UCI SMS Spam Collection (CC BY 4.0), open embedding models from Hugging Face, and the Anthropic Python SDK.
Beginner lessons for LLMs and NLP are being written.
- 1BeginnerA support reply assistant with structured output
- 2BeginnerRoute banking questions to 77 intents
- 3BeginnerSMS spam classifier with an honest baseline
- 4IntermediateA cited question-answering assistant over the Kubernetes docs
- 5IntermediateAn evaluation harness that blocks bad prompt changes
- 6IntermediateAn LLM triage integration driven by helpdesk webhooks
- 7AdvancedFine-tuning versus prompting, decided with numbers
- 8AdvancedPass a customer's security review with an LLM deployment
- 9AdvancedRun a customer pilot end to end