Introduction to AI Engineering
Why it matters if you work with C and C++: AI and machine learning fundamentals, LLMs and modern architectures, RAG, agents and evaluation: the context you need before optimising anything.
While AI applications are written in Python and TypeScript, their execution rests on native code: llama.cpp and the GGUF format for local models, ONNX Runtime and TensorRT for optimised inference, OpenCV for vision, CUDA for accelerators. A C++ developer does not have to become a data scientist; you need to understand enough about models to design the layer that runs them on servers, at the edge and on devices. The examples in these courses are mostly Python; the Edge AI course also has C for microcontrollers.
In the order in which they matter, each with the reason it matters if you work with C and C++. Untick what you already know: the subscription and the price update.
The picture from above: what a model is, how it is trained and how it leaves Python for a native runtime.
Why it matters if you work with C and C++: AI and machine learning fundamentals, LLMs and modern architectures, RAG, agents and evaluation: the context you need before optimising anything.
Why it matters if you work with C and C++: Tensors, autograd, backpropagation, CNNs and Transformers in PyTorch, then GPU training with CUDA and export to ONNX: where the models come from and how they are handed to the runtime you maintain.
The layer where native code decides: models on your own hardware, vision in production, adapted models that have to be served efficiently.
Why it matters if you work with C and C++: The course closest to your work: quantization, pruning and distillation, the LiteRT, ONNX Runtime, Core ML and ExecuTorch runtimes, TinyML on microcontrollers with C code, accelerators such as Jetson and Coral, and small language models with llama.cpp.
Why it matters if you work with C and C++: LoRA and QLoRA, then quantization for inference in GGUF, GPTQ and AWQ and self-hosting: how adapted models are prepared for the engines that run them.
Why it matters if you work with C and C++: Preprocessing with OpenCV, classification, detection and segmentation, then a lesson on deployment and edge optimisation. The code is Python with PyTorch and OpenCV; deployment is where native runtimes take over.
The stage where you tie your components to the rest of the system: the pipeline that delivers models, the tools exposed to agents, the way code is written.
Why it matters if you work with C and C++: Model registry and versioning, serving, deployment strategies and drift monitoring: the pipeline your runtime receives models from and reports metrics to.
Why it matters if you work with C and C++: Protocol architecture, stdio and HTTP transports, authentication and security, so that you can expose systems and hardware to agents safely. The examples are in Python and TypeScript; the protocol is language-agnostic.
Why it matters if you work with C and C++: Agentic coding on large codebases, with deterministic hooks and CI: your builds and tests become the verifiers of generated code.
Not sure what you can skip? Take the free level assessment
The course in the track that ends with a capstone project, from their real modules.
It opens next to the lesson and starts from it. You type or talk to it, and you can listen to the answer.
Included in every plan and in single-course access, within a fair-use limit. It is an artificial intelligence system, not a human teacher; its answers may contain errors. Details in the Terms.
The professor opens next to the lesson, on the section you have reached, with four ways to start: a summary, applying it to your job, mistakes to avoid, or a test.
You select a passage and ask for an explanation. The answer starts from the lesson, and you can listen to it, copy it or save it to your notes.
The ideas of the lesson, point by point, when you ask for them. You can listen to the summary or send it to your notes.
3, 5 or 10 new questions from the lesson you are reading, with an explanation for every answer.
Flashcards made from the lesson: you flip the card and mark what you already knew.
Screenshots from the app, taken in the demo lesson, with prepared answers.
The position of the language, what changes in your work, the tools and what you will be able to do at the end.
Demand for efficient inference is growing in directions that native code covers: models on laptops and phones, real-time vision, industrial devices, environments with tight memory and latency limits. Quantization, runtime selection, accelerator integration and the deployment of vision models are systems problems.
The risk for a C++ developer is isolation: optimising without understanding what the applications above ask for. The courses below start from how models are trained and used and go down towards on-device inference, vision and deployment, where your skill becomes decisive.
Quantization, compact formats and inference without the cloud, for privacy and latency. The Edge AI course tells the story of llama.cpp as proof that a language model could run on a laptop CPU with careful C++ and aggressive quantization.
Detection, segmentation and classification in production, with OpenCV and optimised runtimes. Deployment and optimisation are the native-code half of a computer vision project.
Kilobytes of RAM, integer-only math and no dynamic allocation: TinyML runs quantized models with a small C++ interpreter and a static tensor arena.
With your builds and tests as verifiers. The right context, hooks and CI integration make the difference between help and noise.
These are the skills you practise in the courses of the track; results depend on the time you invest and on your previous experience.
Start the C and C++ trackThe whole C and C++ track fits in a subscription of 10 courses: €319 a month, VAT included. You pick the courses and can change them at every renewal.
Pay for the tier, then pick the courses in your account. You can change them at every renewal.
€99 a course
€99a month €990a year, 12 months of access
under €67 a course
€199a month €1,990a year, 12 months of access
under €52 a course
€259a month €2,590a year, 12 months of access
under €32 a course
€319a month €3,190a year, 12 months of access
under €24 a course
€359a month €3,590a year, 12 months of access
under €16 a course
€399a month €3,990a year, 12 months of access
under €10 a course, across all 50
€499a month €4,990a year, 12 months of access
Total prices, VAT included. Move up anytime and pay only the difference for the days left; move down at renewal. Renews automatically, you stop it anytime from your account; your progress and certificates stay.
Payments are processed by Stripe, a PCI DSS Level 1 certified provider, with 3-D Secure for payer authentication. The connection to this site is TLS-encrypted.
Compare all the subscriptions · The team library, priced per member · Give a month of access as a gift
When you finish the lessons of a course with an average of at least 70% on its quizzes, you issue the PDF certificate from your account, at no extra cost.
A private attestation of course completion. It is NOT a diploma or a state-recognised qualification under Romanian Laws 198/2023, 199/2023 or Government Ordinance 129/2000; employers may take it into account at their own discretion.
The same skills, seen from each ecosystem. The languages close to C and C++ are highlighted.
The Edge AI course has C code for microcontrollers, next to Python, Kotlin and Swift for its other targets. Everything else on this track is in Python, the language in which training and evaluation are orchestrated. The courses are chosen for the areas where native code decides performance: on-device inference, vision and deployment.
The Edge AI course is the entry point: model compression, runtimes, TinyML on microcontrollers, accelerators and small language models on device. The computer vision course adds deployment and edge optimisation, and the fine-tuning course covers quantization for inference.
To read it, yes: training pipelines, model export and evaluation tools are in Python, and the courses use it in their examples. The execution side, runtimes, kernels and hardware integration, stays native.
All the courses recommended here are IT courses. You pick them in a subscription by number of courses: usually 3, 5 or 10 courses a month for one language and stack; there are also 15 and 25 courses, a single course and the full catalog. You pick the courses and can change them at every renewal. The subscription renews automatically, and you can stop the renewal anytime from your account. Every price, VAT included, is shown below and on the pricing page. Every course has a free preview of its first lesson, readable without an account.
8 courses, ~200 hours, in a subscription of 10 courses: €319 per month, VAT included. You can change them at every renewal.
The courses are for educational purposes only: they are not professional advice, and completing them is not a diploma or a state-recognised qualification. The names of languages, tools and products belong to their owners and are mentioned for identification only. Details in the Terms & Conditions.
ChatGPT, OpenAI, Claude, Anthropic, Gemini, Google, Microsoft 365 Copilot, Cursor, Midjourney and the other product and company names mentioned are trademarks or trade names of their respective owners. Cursuri AI is an independent training provider and is not sponsored or endorsed by any of them; our membership in Anthropic's Claude for Startups program does not mean that Anthropic endorses our courses.