@adxtyahq: Good list. I'd add: - Dataset Engineering - https://huyenchip.com/machine-learning-systems-design/toc.html… - Product E…
Summary
A tweet thread compiling essential resources for AI engineering, covering dataset engineering, evaluations, context engineering, agent memory, MCP, observability, inference optimization, and security.
View Cached Full Text
Cached at: 06/09/26, 08:48 AM
Good list.
I’d add:
- Dataset Engineering - https://huyenchip.com/machine-learning-systems-design/toc.html…
- Product Evals - https://developers.openai.com/api/docs/guides/evaluation-best-practices…
- OpenAI Evals - https://developers.openai.com/api/docs/guides/evals…
- Context Engineering - https://anthropic.com/engineering/effective-context-engineering-for-ai-agents…
- Agent Memory & Context Lifecycle - https://platform.claude.com/cookbook/tool-use-context-engineering/context-engineering-tools…
- MCP & Tool Ecosystems - https://modelcontextprotocol.io
- Observability & Tracing - https://docs.langfuse.com
- AI Agent Evaluation - https://deepeval.com/guides/guides-ai-agent-evaluation…
- Inference Optimization (KV Cache, PagedAttention, Batching) - https://docs.vllm.ai
- Security Engineering (Prompt Injection, Agent Safety) - https://owasp.org/www-project-top-10-for-large-language-model-applications/…
- Business Metrics & Product Thinking - https://lennysnewsletter.com
A surprising number of AI engineers spend more time debugging retrieval, context, caching, queues, permissions, and analytics than they do writing prompts.
Machine learning systems design
Source: https://huyenchip.com/machine-learning-systems-design/toc.html
Machine Learning Interviews
Chip Huyen huyenchip.com @chipro
Table of Contents
- Introduction1. Research vs production1. Performance requirements 2. Compute requirements
- Design a machine learning system1. Project setup 2. Data pipeline 3. Modeling1. Model selection 2. Training1. Debugging 2. Hyperparameter tuning 3. Scaling 4. Serving
- Case studies
- Exercises
Mohit Goyal (Harness arc) (@ByteMohit): As an AI Engineer. Please learn
>Harness engineering, not just prompt engineering
>Context engineering, not just long prompts
>Prompt caching vs. semantic caching tradeoffs
>KV cache management, eviction, reuse, and memory pressure at scale
>Prefill vs. decode latency and
Similar Articles
@aiwithmayank: 10 FREE RESOURCES THAT TURN A BEGINNER INTO AN AI ENGINEER Bookmark this whole list. Follow it in order. This is the pa…
A tweet thread curating 10 free resources to learn AI engineering, from Harvard's CS50 AI course to Karpathy's neural networks tutorial, fast.ai, Hugging Face courses, and local tools like Ollama, providing a structured path from beginner to employable skills.
@0xshimei: https://x.com/0xshimei/status/2053306900998181026
The author shares a curated list of 16 frequently used AI skills and tools integrated into their daily workflow, categorized by function, such as information gathering.
@systemdesignone: If you want to become good at AI engineering (in 3 weeks), then learn these 15 concepts: 1 AI Agents: Memory, State & C…
A Twitter thread by @systemdesignone curates 15 essential AI engineering concepts, including a deep dive into AI agent memory, state, and consistency, with links to a newsletter for further learning.
@PrajwalTomar_: I've been building apps with AI for the past year and this design resource list is actually INSANE. If you're building …
A curated list of design resources for developers building AI apps with Lovable, Rork, or Claude.
@AvinashSingh_20: 10 GitHub Repos To Learn in-depth Ai engineering ! 1 :- https://github.com/Avik-Jain/100-Days-Of-ML-Code… 2 :- https://…
A curated list of 10 GitHub repositories recommended for learning AI engineering in depth, covering topics like machine learning basics, LLM applications, and RAG techniques.