Introduction to AI Engineering
Why it matters if you work with Rust: LLMs and modern architectures, APIs, RAG, agents and evaluation: the context you need before going down to the inference level.
Rust has become a language of the performance layer in AI: vector databases such as Qdrant are written in it, Hugging Face maintains candle, a machine learning framework for Rust, and the Model Context Protocol has an official Rust SDK. None of the courses here is written in Rust: their examples are mostly Python. They are on this page because they give you the view from the application down, so you know what runs above the layer you optimise.
In the order in which they matter, each with the reason it matters if you work with Rust. Untick what you already know: the subscription and the price update.
The whole picture of AI systems, so that you know what you are optimising and for whom. Language-independent, with the examples mostly in Python.
Why it matters if you work with Rust: LLMs and modern architectures, APIs, RAG, agents and evaluation: the context you need before going down to the inference level.
Why it matters if you work with Rust: Streaming, error handling, function calling, multi-model routing and productionization: the specification of a model client or gateway you would write in Rust. The examples are in Python.
Why it matters if you work with Rust: Embeddings, chunking, hybrid search and evaluation, with a section on why Qdrant, written in Rust, performs the way it does: so that you design the indexing layer correctly, not just make it fast.
The layer where Rust has the most to say: models on your own hardware, retrieval at scale, fast tools for agents.
Why it matters if you work with Rust: LoRA and QLoRA, quantization for inference (GGUF, GPTQ, AWQ) and serving with Ollama, vLLM and TGI, the last of which has a Rust core: where adapted models have to run efficiently on your infrastructure.
Why it matters if you work with Rust: Vector index internals (HNSW, IVF, quantization), hybrid search, sharding and embedding pipelines at scale: the data-structure end of retrieval, with Python and SQL in the examples.
Why it matters if you work with Rust: Protocol architecture, transports, authentication, testing and containerization. The examples are in Python and TypeScript; the protocol is language-agnostic, and you carry the design to the Rust SDK.
Why it matters if you work with Rust: Attacks on AI systems, guardrails, supply chain and secrets: the requirements for tools and servers exposed to agents.
Why it matters if you work with Rust: Agentic coding from the terminal, headless mode, hooks and CI. The course notes that code-intelligence plugins for typed languages, Rust among them, report type errors to the agent after each edit.
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.
A Rust developer brings two rare things to AI: predictable performance and memory safety in the places where the most data is processed, inference, tokenization and vector indexing.
The risk is blind specialisation: optimising a kernel without knowing how the model is used, what RAG means or how quality is evaluated. The courses below are chosen to give you the top-down picture, from application to inference, and to tie your systems skills to the architecture decisions that matter.
Quantization, formats such as GGUF, hardware sizing and high-throughput serving. Whoever understands both the model and the machine designs inference services that others only configure.
Indexing, hybrid filtering and latency at scale: the problems Qdrant solves in Rust. To design them correctly you need to know what a RAG pipeline looks like from the application end.
Low-latency MCP servers that expose file systems, processes or sensor data to agents, with least-privilege permissions. The protocol has an official Rust SDK.
With the compiler and the tests as deterministic verifiers of generated code. Context, hooks and verification in CI decide whether the agent helps or gets in the way.
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 Rust trackThe whole Rust 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 Rust are highlighted.
No. The examples are mostly in Python, and the MCP course also has a module in TypeScript. The courses are chosen for understanding AI systems from the top down, application, integration, inference, and for protocols such as MCP, which you then implement with the official Rust SDK. That is also why this track has two stages instead of three: it lists only the courses whose substance does not depend on the language.
On this track, the fine-tuning course, with quantization and serving, is the entry point. Outside it, and available in the same subscription, the Edge AI course covers model compression, on-device runtimes and microcontrollers, with examples in Python and some C.
To read it, yes: most examples in these courses are in Python. To adopt it as your main language, not necessarily.
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.