Introduction to AI Engineering
Why it matters if you work with Go: LLMs, APIs, RAG, agents, evaluation and security at concept level: the frame you need to understand what you are serving.
Go is a language of infrastructure, and AI needs infrastructure: model gateways, inference servers, agents that run as services, operations assisted by AI. OpenAI and Anthropic publish official Go SDKs and the Model Context Protocol has an official Go SDK. None of the courses here is written in Go: their examples are mostly Python. They are on this page because they describe the layer above the one you run, and how AI enters operations.
In the order in which they matter, each with the reason it matters if you work with Go. Untick what you already know: the subscription and the price update.
The mental model of LLMs and of AI applications, so that you design the layer underneath correctly. Language-independent, with the examples mostly in Python.
Why it matters if you work with Go: LLMs, APIs, RAG, agents, evaluation and security at concept level: the frame you need to understand what you are serving.
Why it matters if you work with Go: Gateway, queue-based and sidecar patterns, streaming over SSE, circuit breakers, multi-provider fallback, rate limiting, caching and OpenTelemetry tracing: in effect the specification of a model gateway, which you then implement in Go. The examples are in Python.
Why it matters if you work with Go: Protocol fundamentals, stdio and HTTP transports, OAuth 2.1, testing, containerization with Docker and Kubernetes, and CI/CD. The example servers are in Python and TypeScript; the course itself points out that the protocol is language-agnostic and that an internal server can just as well be written in Go.
The stage where AI enters the operation of the platform and where you answer for quality, cost and security.
Why it matters if you work with Go: Observability with OpenTelemetry, Prometheus and Grafana, anomaly detection, AI-assisted incident response and root cause analysis, AI in CI/CD and infrastructure as code, ChatOps and Kubernetes operations: the course written for platform teams.
Why it matters if you work with Go: The self-hosting half is yours: quantization for inference (GGUF, GPTQ, AWQ), serving with Ollama, vLLM and TGI behind OpenAI-compatible endpoints, and cost and hardware planning.
Why it matters if you work with Go: Model serving patterns, deployment strategies (canary, shadow, A/B testing), drift monitoring and GPU cost: the lifecycle your platform has to support.
Why it matters if you work with Go: Regression tests in CI/CD, online A/B testing and quality-drift monitoring: answer quality treated like any other operational signal.
Why it matters if you work with Go: Prompt injection, excessive agency, supply chain, secrets and denial of service against models: the security requirements for gateways and for tools exposed to agents.
Why it matters if you work with Go: Agentic coding from the terminal, headless mode, hooks and CI integration. The course notes that code-intelligence plugins for typed languages, Go among them, let the agent catch type errors 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 Go developer brings what AI projects often lack: small, fast, observable services that survive real traffic. Gateways that route between models, cost limits per client, response caching, low-latency MCP tools, agents that run as services: all of these are systems problems, not data science problems.
The risk is staying at the infrastructure level without understanding what runs on it. Someone who does not know how a model behaves, what RAG means or how answer quality is evaluated cannot design the layer underneath correctly. The courses below give you that mental model and tie it to operations, where you are already at home.
Routing between providers, retries, streaming, cost limits, caching and compliant logging: a typical Go service, with the twist that the answer is non-deterministic and cost is per token.
Internal services become tools for agents and assistants, with authentication and least-privilege permissions. The protocol is language-agnostic and has an official Go SDK.
Alert triage, root cause analysis, log and trace analysis, ChatOps and Kubernetes operations. Platform teams need to know both what these tools can do and where they must stop.
Quantization, hardware sizing and OpenAI-compatible endpoints. Whoever operates these services decides the cost and the confidentiality of the whole platform.
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 Go trackThe whole Go 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 Go are highlighted.
No. The examples are mostly in Python, and the MCP course also has a module in TypeScript. The courses are chosen for architecture, protocols and operating practices, which you then implement with the official Go SDKs for OpenAI, Anthropic and MCP. 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.
Yes. The AIOps course is written for operations teams, and the fine-tuning and MLOps courses cover the platform decisions: serving, cost, monitoring. The foundations give you the context, so that you do not operate blind.
The course on fine-tuning open-source LLMs: it covers open-model licenses, quantization for inference, serving with Ollama, vLLM and TGI, and cost and hardware planning. The MLOps course adds serving patterns, deployment strategies and monitoring.
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.
9 courses, ~225 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.