AI Engineer
Build applications on top of language models: ground them in real evidence, let them use tools, serve them affordably, and prove they still work after a change.
Ship an LLM feature you can evaluate, cost, debug, and defend — rather than a demo that works until the inputs change.
Python for Data Work
Turn Python records into trustworthy, analysis-ready tables with NumPy and pandas.
Build the engineering foundation
Start with Python, probability, classical ML, and the software boundaries a reliable AI application needs.
- AI & Machine LearningPython for Data WorkTurn Python records into trustworthy, analysis-ready tables with NumPy and pandas.
- AI & Machine LearningProbability and Statistical ReasoningBuild probability from cases, then use it to reason about repeated observations and evidence.
- AI & Machine LearningClassical Machine LearningTake one prediction problem through data cleaning, modeling, deployment, and monitoring.
- AI & Machine LearningSoftware Engineering for AI ApplicationsStructure, test, and debug the software around a model instead of treating the model call as the whole product.
- AlgorithmsBig-O NotationCount how much work code performs, then describe how that work grows with the input.
- AlgorithmsArraysLearn how indexed storage works, what each array operation costs, and how one safe pass grows into in-place and matrix algorithms.
- AlgorithmsStringsTreat text as an indexed sequence first, then add immutable output, word boundaries, symmetry, runs, direct search, and grammar one idea at a time.
- AlgorithmsHash Tables and SetsProgress from remembering whether a key exists to storing counts, complements, canonical signatures, and one-to-one mappings.
Understand the model and build retrieval
Learn the neural and language-model foundation, then build a retrieval path that supplies evidence and can be measured separately from generation.
- AI & Machine LearningDeep Learning FoundationsLearn the computation underneath transformers before attention, fine-tuning, and serving add more machinery.
- AI & Machine LearningLLM FoundationsUnderstand what a language model actually computes, so the cost, latency, and failure modes of an LLM feature stop being surprises.
- AI & Machine LearningRAG and Retrieval SystemsRetrieve useful evidence, ground generated answers, and measure retrieval separately from generation.
Add tools, evaluation, and system design
Give the model controlled actions, measure the behavior that matters, and connect product requirements to an end-to-end architecture.
- AI & Machine LearningAgents and Tool UseDecide when a loop beats a pipeline, design tools a model can call correctly, and contain an agent that will eventually be wrong.
- AI & Machine LearningOperating LLM Systems in ProductionEvaluate LLM behavior across prompts, judges, RAG components, distribution shifts, guardrails, and long contexts.
- AI & Machine LearningApplied AI System DesignDesign a complete model-backed product and defend its interfaces, measurements, trade-offs, and failure modes.
- AI & Machine LearningAI Security, Safety, and PrivacyThreat-model the complete AI system: its data, prompts, models, retrieval layer, tools, users, and logs.
Go deeper into training and inference
Study data scaling, post-training, serving internals, and multimodal models when the role expects work below the application layer.
- AI & Machine LearningLLM Training, Data, and ScalingUnderstand what pretraining consumes, how data quality changes the result, and why large-model training is a distributed-systems problem.
- AI & Machine LearningPost-training and AlignmentLearn how demonstrations, preference rankings, and carefully constrained updates turn a pretrained model into an assistant.
- AI & Machine LearningLLM Serving and Inference EconomicsFind out where the latency and the money actually go, then change the number instead of guessing at it.
- AI & Machine LearningMultimodal ModelsUnderstand how models connect language with images, audio, and video—and where cross-modal systems fail.