NLP and LLM Engineer Professional Certificate

From tokens and corpora to transformers and large language models: build systems that understand, search and generate language.

Start with Python and text corpora, then learn the statistical methods behind classic natural language processing and the ways text becomes vectors, from bag-of-words to embeddings. Go on to transformers and large language models, prompting and LLM application design, semantic search with vector databases, retrieval-augmented generation and agents, and fine-tuning open models for your own tasks. Every course has hands-on labs and a capstone project your instructors review.

Prepares you for

NLP engineer, LLM engineer, Machine learning engineer, Applied scientist

8 courses in this Professional Certificate

  • NLP Foundations with Python and Corpora: Load corpora, clean and normalise raw text, tokenise it with regular expressions, and count, compare and model words in Python with NLTK. (Beginner, about 17 hours)
  • Statistical NLP: Models, Parsing and Information Retrieval: Classify text with Naive Bayes and logistic regression, build word vectors from counts, tag with hidden Markov models, parse with probabilistic grammars, and rank documents with TF-IDF and BM25. (Intermediate, about 22 hours)
  • Text Representation: From Vectors to Context: Represent text as numbers, from one-hot vectors, bags of words and TF-IDF to word2vec, fastText and the contextual embeddings of transformers, and learn to visualise and question what they encode. (Intermediate, about 17 hours)
  • Transformers and Large Language Models: Build attention and transformer blocks from scratch, understand how large language models are pretrained, aligned and scaled, and fine-tune, decode and evaluate them with Hugging Face. (Advanced, about 23 hours)
  • Prompting and LLM Application Design: Design LLM features that hold up in production: structured outputs, reasoning, retrieval, tools, guardrails and evaluation, built in Python on the Claude API. (Intermediate, about 20 hours)
  • Vector Databases and Semantic Search: Build semantic search that's fast and measurably right: embeddings, exact and approximate indexes, compression, hybrid ranking, filtering and vector databases. (Intermediate, about 18 hours)
  • Building RAG and Agentic Systems: Build retrieval-augmented and agentic AI systems that hold up: measured retrieval, hybrid search and re-ranking, tool-using agents with memory and plans, and multi-agent teams that check each other's work. (Advanced, about 22 hours)
  • Fine-Tuning Open Language Models with LoRA: Decide when fine-tuning pays, prepare chat data properly, and fine-tune open models with LoRA and QLoRA, from the maths and a LoRA layer of your own to transformers, peft, evaluation and serving. (Advanced, about 19 hours)