Fig. 1 — InferQuest, the verified path into LLM serving
Become an inference engineer.
A free, open inference engineering roadmap from “what’s a KV cache” to a signed offer — built from real job-market research, with milestones that are verified, not checked off.
The full curriculum is open to browse — sign in (free) to track progress, take the drills, and unlock the verifiers.
What is InferQuest?
InferQuest is a free, open, non-commercial web application for learning inference engineering — the craft of serving large language models fast and cheaply. It organizes a complete curriculum into quests and tasks, 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, 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.
Checkboxes are cheap. These aren’t checkboxes.
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
A local harness grades your attention, KV cache, Triton softmax, tiled matmul, flash attention, quantizer, and ring all-reduce on your own hardware — correctness against references AND measured speed.
Merged-PR checks
The open-source milestones verify against the GitHub API that your PRs into vLLM, SGLang, FlashInfer & co. actually exist, actually merged, and aren't typo fixes.
Graded interview drills
KV-cache sizing math, rooflines, speculative-decoding acceptance, parallelism tradeoffs — graded server-side, answers never shipped to your browser.
The journey
Level up from Token to Inference Engineer through ten phases — each quest unlocks as its prerequisites near completion.
Frequently asked questions
>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.
>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?
The full path is 129 tasks across 28 quests and 10 phases (15,700 XP). An experienced software engineer studying part-time should expect roughly six months to a year 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.
The market pays for proof, not promises.
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.