LeetLLMContent EngineeringAI Engineering+2
How We Built LeetLLM
Inside LeetLLM's Git-backed curriculum: reviewable article bundles, generated figures, user-owned state, and the checks between a source edit and a deployed page.
12 min
Read
Blog
AI Engineering Blog
Practical notes on LLM systems, evaluation, agents, inference, and developer workflows.
19 postsRSS
AI CodingDeveloper ToolsCost Optimization+5
AI Coding Plans: Prices and Limits
Compare AI coding subscription prices, annual commitments, seat minimums, usage windows, and overflow costs, then calculate a budget from reviewed work.
13 min
Local LLMQwen3.6Unsloth+3
Run Qwen3.6 Locally with Unsloth GGUF
Build a pinned llama.cpp server, verify a Qwen3.6 GGUF download, and test a local text endpoint. Understand memory limits before adding context, MTP, or vision.
12 min
CareerPortfolioProjects
AI Engineer Portfolio Projects for Interviews
Five focused AI engineering projects, with concrete experiments, inspectable artifacts, and failure cases that make the work worth discussing.
12 min
CareerAI EngineeringRoadmap
How to Become an AI Engineer from Zero in 2026
Start with programming, grow one useful project, and choose deeper study from the work you want to do. A practical path without a hiring countdown.
13 min
DeepSeekOpen ModelsAI Infrastructure+2
DeepSeek V4: Facts, Claims, and Fit
What DeepSeek V4's release notes, parameter counts, benchmark tables, and live prices actually tell you about deploying Flash 0731 or Pro 0813.
11 min
OpenClawAI Coding PlansCost Optimization+4
Best AI Plans for OpenClaw in 2026
Choose an OpenClaw plan by permitted workload, credentials, quotas, and paid fallback. Compare dated prices and calculate request costs without confusing them with task costs.
11 min
Local LLMOllamaGemma 4+2
Run Gemma 4 Locally with Ollama
Run Gemma 4 locally with Ollama: pick an exact tag, leave memory for context, verify placement with ollama ps, and benchmark the native API.
15 min
InferencevLLMSGLang+5
Choosing an LLM Inference Engine
Compare vLLM, SGLang, TensorRT-LLM, Ollama, and llama.cpp by deployment surface, checkpoint recipes, latency, throughput, and operating cost.
16 min
AI EngineeringInterview PreparationArchitecture+1
50 LLM Interview Questions for 2026
Fifty LLM engineering questions that connect model mechanics to serving, retrieval, agents, evaluation, and safety through evidence and failure diagnosis.
34 min
AI EngineeringToolsDeep Dive+1
AI Coding Assistants in 2026
Compare Cursor, Codex, Copilot, and Claude Code through one authorization change. Choose by operating mode, review surface, cost meter, and team controls.
13 min
CareerCompensation
AI Engineer Salary Guide 2026
Compare AI engineering pay without mixing BLS wages, posted salary, and total compensation. Match role family, level, location, equity terms, and source date first.
16 min
LLMsAI EngineeringDeep Dive+2
Open-Weight vs Closed API LLMs
Separate model rights from deployment control, evaluate the complete data path, and compare cost per accepted answer rather than API tokens against GPU rent.
11 min
Context WindowsLong ContextBenchmarks+2
Million-Token Context Windows
Million-token windows can hold a bounded corpus, but capacity doesn't guarantee reliable retrieval. Measure effective context, watch length-based prices, and choose between full context and RAG.
13 min
AgentsDeep DiveTutorial
How to Build an AI Agent from Scratch
Build a Python agent that follows configuration references, then test its tool permissions, history, recovery, and stop conditions before connecting a live model.
12 min
AI EngineeringRAGFine-Tuning+1
RAG vs Fine-Tuning vs Prompting
A policy assistant gives the wrong answer. Should you rewrite its prompt, retrieve better evidence, or train it? A controlled evidence swap reveals which experiment to run next.
12 min
AI EngineeringCareerIndustry
What Does an AI Engineer Actually Do?
Follow a support assistant from a wrong answer to a tested fix. See how applied AI, ML platforms, and research engineering divide the work.
11 min
BenchmarksEvaluationSWE-bench+2
Understanding SWE-bench
Read SWE-bench as a repository-repair experiment: trace a patch through grading, compare variants and attempt rules, and check the limits of public scores. Updated for Multimodal v2.
18 min
CareerInterview Prep2026
How to Prepare for ML & LLM Engineering Interviews in 2026
Prepare for the interview you're actually taking: confirm the format, attempt representative problems, and use concrete coding, ML, and LLM debugging exercises to find gaps.
12 min