Show HN: Free Inference Engineer and Model Training Roadmap

# InferQuest — Become an Inference or Training Engineer Source: [https://inferquest.org/](https://inferquest.org/) InferQuest — verified paths into LLM serving and training Two free, open roadmaps built from real job\-market research: make models**fast and cheap**in production, or make them**as good as possible**on the cheapest hardware — with milestones that areverified, not checked off\. The full curriculum is open to browse — sign in \(free\) to track progress, take the drills, and unlock the verifiers\. 01 **InferQuest**is a free, open, non\-commercial web application for learning inference engineering and LLM training\. It offers two paths — serving large language models fast and cheaply, and training them as good as possible on minimal hardware — organized into quests and tasks\. It tracks your progress with XP, levels, and streaks, drills you with graded quizzes and spaced\-repetition reviews, and automatically verifies major milestones like deployed endpoints, GPU kernels, training runs, and merged open\-source pull requests\. Signing in \(with Google or email\) is used only to save that progress to your account — see the[privacy policy](https://inferquest.org/privacy)\. 02 ### Live endpoint probes Deploy an OpenAI\-compatible endpoint — your own engine, then production vLLM — and InferQuest probes it for real: streaming framing, usage accounting, max\_tokens cutoffs, error shapes, latency targets\. ### GPU\-graded kernels & training runs A local harness grades your kernels — attention, KV cache, Triton softmax, flash attention, quantizer, ring all\-reduce — AND your training runs: first convergence, a measured ≥1\.5× speedup, an adapter fine\-tune that must not forget, all under fixed token budgets on your own hardware\. ### Merged\-PR checks The open\-source milestones verify against the GitHub API that your PRs into vLLM, SGLang, FlashInfer, TRL, torchtitan, nanochat & co\. actually exist, actually merged, and aren't typo fixes\. ### Graded interview drills KV\-cache sizing math, rooflines, speculative\-decoding acceptance, scaling\-laws and data\-curation calls, parallelism tradeoffs — graded server\-side, answers never shipped to your browser\. 03 Everyone starts in**Foundations**— transformer internals, GPU architecture, kernels — then branches\. Level up from**Token**to**Foundation Model**on one shared XP ladder; the path titles — Inference Engineer, Training Engineer — are earned as certificates\. 04 What does an inference engineer do?Inference engineers make large language models fast and cheap to serve in production: writing and tuning GPU kernels, managing KV\-cache memory, batching requests, quantizing weights, and operating engines like vLLM, SGLang, and TensorRT\-LLM against latency and cost targets\. It's one of the fastest\-growing specialist roles in AI infrastructure\. What skills do I need to become an inference engineer?The core inference engineering skills are transformer internals \(attention, KV caching, sampling\), GPU architecture and CUDA or Triton kernel writing, quantization, continuous batching and paged attention, distributed serving \(tensor and pipeline parallelism\), and profiling with tools like Nsight\. InferQuest's roadmap covers all of these in order, with a verifier gating each major skill\. Can InferQuest teach me to train my own LLM?Yes — the Model Training path covers exactly that: backprop and optimizers from scratch, data curation with real Common Crawl pipelines, scaling\-laws math, the NanoGPT\-speedrun efficiency toolkit \(Muon, FP8, fused kernels\), a GPT\-2\-class pretraining capstone you can run on one consumer GPU or ~$50 of rented compute, then SFT, LoRA, DPO, and GRPO post\-training on a single GPU\. It leads to the pretraining, post\-training, and RL engineering roles labs are actively hiring for\. Is InferQuest free? Do I get a certificate?InferQuest is completely free and open\. There is no paper certificate — instead, milestones are auto\-verified: live probes against your deployed endpoint, GPU\-graded kernel submissions, and merged\-PR checks against real open\-source repos\. The result is a portfolio of receipts, which hiring teams weigh far more than a certificate\. How long does the roadmap take?Both paths together span 182 tasks across 38 quests \(21,740 XP\), sharing a common trunk of fundamentals\. An experienced software engineer studying part\-time should expect roughly six months to a year for one path end to end — less if you already know PyTorch and CUDA, since early phases are skimmable\. Do I need my own GPU?For the kernel\-engineering phases, yes — the grading harness runs on your own hardware, and any modern NVIDIA GPU works\. Everything before that \(transformer internals, the inference\-engine capstone, quizzes and drills\) runs on CPU or free cloud notebooks\. Every verified milestone leaves a receipt: probe results, harness metrics with your GPU’s name on them, merged\-PR evidence\. That’s a portfolio, not a certificate\. InferQuest — open, gamified paths into LLM inference and training engineering, with verified quests\. [Privacy](https://inferquest.org/privacy)[Terms](https://inferquest.org/terms)[GitHub](https://github.com/jneums/inferquest)