AI Engineering logopeterindia.net
Knowledge Hub

AI Engineering

A hub for AI engineering: the guides and directories on this site for building applications on top of foundation models, from prompts and retrieval to agents, inference, evaluation, operations and safety.

57 topics•8 categories•Updated November 22, 2026

AI engineering is the work of building, serving and operating applications on top of foundation models. It sits between machine learning research and software engineering: prompts and context, retrieval, agents and tools, inference and cost, evaluation and testing, observability and guardrails. This hub groups the related pages on this site into seven areas. Each card links to a guide or directory that is updated on its own page.

Building Blocks: Prompts, Context, RAG and Models

14 entries

The core techniques and components of an AI application: prompts and context, retrieval, embeddings and rerankers, fine-tuning, and the stores behind them.

01Prompt EngineeringDirectory of prompt engineering in 2026: official guides from Anthropic, OpenAI, Google and Microsoft, core techniques and papers. 02Context EngineeringDirectory of context engineering in 2026: foundational guides, context windows and long-context limits, memory systems, retrieval and RAG. 03Harness EngineeringGuide to harness engineering for 2026: the Thoughtworks Radar theme, OpenAI and Martin Fowler on harnesses, agent plugins, skills. 04LLM FrameworksA directory of widely used LLM frameworks in 2026: application and orchestration, agent, prompt programming, low-code builders. 05Embedding ModelsGuide to embedding models for search and RAG: Gemini Embedding 2, OpenAI, Cohere Embed 5, Voyage 4, Qwen3-Embedding, EmbeddingGemma 2. 06Multimodal Embedding ModelsGuide to multimodal embedding models: Gemini Embedding 2, Amazon Nova, Cohere Embed 5, Voyage, Qwen3-VL-Embedding, ColPali, SigLIP 2. 07Reranker ModelsGuide to reranker models for search and RAG: Cohere Rerank 5, Voyage, Jina, Qwen3-Reranker, BGE, mxbai, cross-encoders and ColBERT. 08LLM Fine-Tuning TechniquesLLM fine-tuning techniques: LoRA, LoRA-FA, VeRA, Delta-LoRA, LoRA+, DoRA, QLoRA, TinyLoRA, DPO and GRPO, with parameter counts, tools. 09Open-Source RAG StackThe open-source RAG stack in seven layers: Next.js, LangChain, Llama, Milvus, pgvector, Sentence Transformers, Airflow and more. 10Production-Ready RAG ArchitectureProduction-ready RAG architecture: ingestion, query understanding, chunking, hybrid retrieval, reranking, grounded answers, pgvector. 11Efficient RAG ArchitectureA practical guide to efficient RAG architecture: ingestion, query understanding, context optimisation and grounded generation. 12RAG vs OKF vs Agentic RAGRAG vs OKF in 2026: how retrieval, AI agents, agentic RAG and Open Knowledge Files fit together, with specs, papers, tools and vector. 13Vector DatabasesDirectory of widely used vector databases and vector search for 2026: Pinecone, Weaviate, Milvus, Qdrant, Chroma, pgvector, Elasticsearch. 14Open-Source Embedded Databases for AI Agents15 open-source embedded databases for AI agents: Relate, SQLite, DuckDB, PGlite, LanceDB, Chroma, sqlite-vec and more, with licences.

Agents and AI-Assisted Coding

9 entries

Frameworks, protocols and tools for building agents, and the coding agents engineers use day to day.

Inference, Serving and Cost

11 entries

Running models in production: inference engines and platforms, gateways and routers, and optimization of latency, memory and tokens.

24Open-Source LLM Inference EnginesGuide to open-source LLM inference engines in 2026: vLLM, SGLang, TensorRT-LLM, llama.cpp, Ollama, MLX, plus Strata. 25LLM Inference Platforms and ToolsLLM API providers, inference hosts, GPU clouds, routers and local apps, plus a comparison of vLLM, SGLang, TensorRT-LLM. 26Production AI Inference StackA technical walkthrough of the production AI inference stack: why vLLM, what llm-d adds for distributed inference. 27Distributed LLM InferenceGuide to distributed LLM inference on Kubernetes: vLLM, llm-d, cache-aware routing, prefill/decode split, KV cache offloading and TornadoVM. 28On-Device Inference EnginesGuide to on-device inference engines in 2026: Mirai uzu for Apple Silicon, MLX, llama.cpp, ExecuTorch, LiteRT, ONNX Runtime, MLC LLM. 29ML Model Serving ToolsDirectory of tools for serving machine learning models: Kubernetes-native servers such as KServe and Seldon. 30AI Gateways and LLM GatewaysLink-verified guide to 32 AI and LLM gateway platforms for routing, governing and securing LLM, MCP and agent traffic. 31AI Model Routers11 AI model routers: OpenRouter, Foundry, Cursor, Ramp, Copilot Fusion, Sakana Trinity, plus open-source RouteLLM, vLLM Semantic Router. 32Token Optimization ToolsDirectory of token optimization tools for LLM apps and AI coding agents: codebase knowledge graphs, output sandboxing, CLI compression. 33AI Model Optimization TechniquesAI model optimization techniques for 2026: pruning, quantization, distillation, LoRA, speculative decoding, continuous batching. 34AI Model Quantization TechniquesGuide to AI model quantization in 2026: PTQ and QAT methods (GPTQ, AWQ, SmoothQuant), rotation and second-order methods.

Evaluation and Testing

5 entries

How to know whether an AI system works: LLM and agent evaluation methods, test tooling and metrics.

Operations and Observability

7 entries

Keeping AI systems running: LLMOps and MLOps, monitoring, tracing and observability.

Safety and Guardrails

2 entries

Controls that keep agents and LLM applications inside safe limits.

Learning Resources

4 entries

Curated repositories and roadmaps for learning the craft.

Related Pages

5 entries

Related hubs and directories on this site.