← back
[Workshop] AI Engineering 101
Takeaway
The minimum AI-engineer base layer is calling LLM APIs, embeddings, code gen, image gen, and STT — wired into a real product like a Telegram bot.
Summary
- Latent Space University intro workshop run alongside the AI Engineer Summit to level-set newcomers; structured around 5 topics: calling LLM APIs, embeddings/tokens, code generation, image generation, voice-to-text.
- Hands-on build: a Telegram bot wired to multiple AI APIs (uses Telegram BotFather to mint a bot token, then plugs into OpenAI/etc).
- Argues AI Engineer demand (Google Trends-style growth) will outpace ML Engineer demand because more people can build product with these models than work on the underlying infra.
- Format: branch checkpoints in the GitHub repo so attendees can catch up after each step; emphasis on understanding concepts over keeping pace with code.
ai-engineeringfundamentalsworkshop
Original description
Introductory course for AI Engineers, free for preregistered Summit attendees. Build 5 small projects covering GPT3 API Basics, Prompt Tooling and Memory , Code Generation with GPT4, Image Generation with Dall-E, Stability AI, Lexica, and Midjourney, Speech-to-Text with Whisper. First public run through of the Latent Space University material led by instructor Noah Hein!