miatz™
Verify a credentialLog inSit ChuunSit Chuun
  • Learners
  • Mentors
  • Business
CoursesApplied AIProgramResidencyPlaygroundsWar RoomsXookAtlasReadiness Check
miatz

The AI-era engineering institute. The machines got fast — we train the drivers. Real work, a daily loop that compounds, and a record that proves you can think.

Toggle theme
Explore
  • Courses
  • Applied AI
  • Program
  • Residency
  • Playgrounds
  • War Rooms
  • Xook
  • Atlas
  • Readiness Check
  • Tokenizer Lab
  • Chunking Lab
  • Prompt Anatomy
  • Calibration Lab
  • All playgrounds →
Learn
  • Courses
  • The Method
  • The Residency
  • Chuun · Entrance Examination
  • Manifesto
  • The Itz'at credential
  • Verified engineers
  • Playground Catalog
  • AI Use-Case Atlas
  • AI Readiness Check
  • Guides
  • Glossary
  • Compare approaches
  • Blog
  • What's New
For teams
  • For Students
  • For Mentors
  • For Business
  • Classroom migration
  • Miatz Index
  • API reference
  • Sit Chuun
  • Log in
Company
  • About
  • Experts
  • Why it's free
  • Pricing
  • FAQ
  • Contact
  • Privacy Policy
  • Terms of Service
  • Your data & privacy requests
  • Grievance redressal
  • Security & disclosure
  • Subprocessors
  • Data Processing Agreement
Take miatz with you

The Android app is live. iOS is on the way.

Available on AndroidGet it on Google Play
Not yet on iPhoneiOS — use the web app

Miatz Private Limited

Registered office:
C-101, Lotus Tower, Arge Urban Bloom, 30/A, 4th Main, 2nd Stage, Yeswanthpur, Bengaluru, Karnataka 560022, India
CIN:
U62013KA2026PTC226418
GSTIN:
29AAVCM3922D1Z6
Phone:
+91 82802 73456
Email:
hello@miatz.com
Website:
miatz.com
Grievance Officer:
Aishwarya · aishwarya@miatz.com · replies within 30 days
© 2026 miatz · Miatz Private Limited · Built in Bangalore·PrivacyTerms

miatz™, Itz'at™, Tuukul™, T'aan™, Kanan™, Xook™ and Chuun™ are trademarks of Miatz Private Limited (registrations in progress) · what the names mean

miatz
AI Engineering · 400-level

LLMOps: Cost, Latency, Observability

Sit Chuun — free All modules
AIE-4023 creditselectivebadge: operatorprereqs: AIE-301
Start this course — free

Earn the operator credential

What's inside

Sections & lessons

01

Routing & caching strategies

  • Sending each request to the cheapest model that still passesconcept45 min
02

Cost-attribution & the 1000x slider

  • Turning a $0.02 demo run into a visible daily cost cliffconcept60 min
03

Token-level latency

  • Racing several models on the identical taskconcept60 min
04

Quantization quality-delta at scale

  • What int8/int4 actually costs in eval scoreconcept60 min
05

Observability: traces & cost attribution

  • Reading a production trace back to its dollar costconcept45 min
06

Lab + eval-gate: routing strategy under a quality floor

  • Recommend a routing/caching plan that survives scale (Operator badge)concept120 min
Start this course — free
Learn it from the inside

This module's playgrounds

  • Cost & Latency Bench

    Coming soon

    Watch a demo's pennies turn into a production cost cliff.

    AiAIE-402BYOK AIMedium
    Play it now

  • System Design Studio

    Coming soon

    Build an AI pipeline, then watch traffic find its breaking point.

    AiAIE-403BYOK AIDeep
    Play it now

  • Model Grand Prix

    Coming soon

    Five models race one task, cost ticking live.

    AiAIE-402BYOK AIDeep
    Play it now

  • Can You Actually Run This?

    Live

    Pick a model and your GPU. We do the honest math.

    AiAIE-110BYOK AIQuick
    Play it now
AI Engineering

Next in this path

Where this specialization goes from here — in (level, code) order.

  • AIE-403

    AI System Design

    3 creditselectivebadge: architect
    Start
  • AIE-490

    Capstone: Ship & Evaluate an AI System

    4 creditscapstonebadge: ai-engineer
    Start
Vocabulary

Key concepts in this course

Cost Per Token Latency Percentiles (p50/p95/p99) Quantization Prompt Caching KV Cache

Compare related approaches

Closed vs Open-Weight Models INT8 vs INT4 Quantization
Optional · watch & try

Go deeper, elsewhere

Hand-picked public explainers and open tools — always optional, never required, never graded.

LLM Inference: Cost vs. Latency vs. ThroughputFrames the three-way tradeoff every serving decision makes Cut Your LLM Costs and Latency up to 86% with Semantic CachingConcrete caching technique with a measured before/after Fix Your LLM Latency: What Actually Works in ProductionProduction-grade latency debugging checklist Artificial Analysis — LLM Price CalculatorCompare real token pricing and speed across model providers

This module ends in a gate you can fail.

That's what makes passing it mean something. Sit Chuun, get placed, and start earning.

Sit Chuun — free All modules