@aiDotEngineer ยท English

๐Ÿค– AI Engineer

AI Engineer conference talks, workshops, and panels. Frontier labs, agents, RAG, evals, the AI engineering toolchain.

678 videos ยท 20 topics ยท Browse by category โ†’ ยท YouTube โ†— ยท NotebookLM โ†—

Topics

๐Ÿค– Agents 110

LLM agents that plan, call tools, and act in loops. LangGraph, CrewAI, AutoGen, custom orchestration, multi-agent systems, agent reliability.

agentsmulti-agentmcpworkflows

๐Ÿ’ป Code Generation 79

AI coding tools and agents. Cursor, Devin, Copilot internals, SWE-bench, agentic refactoring, repo-scale understanding.

coding-agentscode-generationai-codingagents

๐Ÿ“ Evals 58

How to actually measure LLM and agent quality โ€” golden sets, LLM-as-judge, regression gates, production tracing, observability.

evalsobservabilityagentsllm-as-judge

๐Ÿ’ผ AI Business 54

Going to market with AI. Pricing, GTM, build-vs-buy, moats, enterprise adoption, vertical agents, ROI stories.

ai-businessstartupsenterprise-aihiring

๐Ÿ”Ž RAG 48

Retrieval-augmented generation โ€” chunking, embeddings, hybrid search, rerankers, citation, evaluation. The dominant pattern for grounding LLMs in private data.

raggraphragneo4jknowledge-graphs

๐Ÿ’ฌ LLM Apps 47

End-to-end LLM-powered applications. Prompt + context plumbing, structured outputs, retry & repair, user feedback loops.

agentsllm-appsevalsrag

๐Ÿ—๏ธ AI Infrastructure 36

GPU clusters, training stacks, autoscaling inference, data pipelines, feature stores, observability for AI workloads.

agentsinfrastructuregpusai-infrastructure

โœจ Product & UX 30

Designing AI features users actually want. Latency, trust, streaming, citations, undo, the "AI moment" in a product.

productdesignmultimodalagents

๐Ÿ”Œ MCP 30

Model Context Protocol โ€” how clients (Claude, Cursor, IDEs) connect to servers that expose tools, resources, and prompts.

mcpagentsanthropicenterprise

๐Ÿง  Foundation Models 30

Frontier LLM training, architecture choices, scaling, post-training (SFT/RLHF/DPO), evaluation, releases from OpenAI, Anthropic, Google, Meta, Mistral, etc.

foundation-modelsgeminiopen-weightsgemma

โšก Inference & Serving 28

Throughput and latency engineering. Continuous batching, paged attention, quantization, speculative decoding, vLLM/TensorRT/SGLang.

inferenceon-devicegpunvidia

๐ŸŽ™๏ธ Voice 26

Real-time voice AI. ASR (Whisper), TTS, turn detection, latency, voice agents for phones, support, accessibility.

voicepipecatagentsvoice-ai

๐ŸŽฏ Fine-Tuning 20

Adapting pre-trained models โ€” full SFT, LoRA/QLoRA, DPO, preference tuning. When fine-tuning beats prompting + RAG.

fine-tuningrlunslothlora

๐Ÿ›ก๏ธ Safety & Alignment 19

Prompt injection defenses, jailbreak resistance, hallucination mitigation, PII handling, red-teaming, responsible scaling.

securitysafetyred-teamingprompt-injection

๐ŸŽจ Multimodal 18

Vision-language models, video understanding, image generation, multimodal agents. GPT-4V, Claude vision, Gemini, open-source VLMs.

multimodalvideo-generationveorobotics

๐Ÿ› ๏ธ Tools & Frameworks 16

The AI engineering toolchain โ€” LangChain, LlamaIndex, DSPy, LangGraph, LangSmith, Braintrust, Inspect, AGENTS.md.

agentstypescriptdspytool-calling

โœ๏ธ Prompt Engineering 12

Prompting patterns โ€” few-shot, chain-of-thought, ReAct, structured output, prompt management at scale.

prompt-engineeringevalsprompt-optimizationclaude

๐Ÿงฎ Embeddings & Vector DBs 6

Embedding models, chunking, hybrid retrieval, vector store choice (Pinecone, Qdrant, Weaviate, pgvector), reranking.

embeddingsvector-searchrecsysmultimodal

๐Ÿ“ฆ Misc 6

Talks that span multiple themes, panels, opening keynotes, and general AI Engineer content.

communityroboticshumanoidopen-source

๐Ÿ”ฌ Research 4

Frontier research talks โ€” new architectures, training techniques, theoretical insights, paper deep-dives.

agiworld-modelscode-generationmeta-fair