goabiaryan

Cohort 1

Pikachu

Special Access

Most engineers load models with Hugging Face then serve something basic and get stuck on cost, latency, or scale. In this course, we will 

ML Research Engineer and Book Author 

Abi Aryan

Founder and Research Engineering Lead @ Abide AI 

AI Systems Design & Inference Engineering

Cloud Engineer

Software Engineer

Researcher

AI Engineer

Vice President, Data Science Practice Lead

Software Developer

AI Engineer/ AI Scientist

Senior AI Engineer

O'Reilly Media

@Packtpub

[𝐮𝐩𝐝𝐚𝐭𝐞𝐬] 𝐂𝐨𝐡𝐨𝐫𝐭 𝟏: 𝐅𝐞𝐛 𝟐𝟏 - 𝐀𝐩𝐫𝐢𝐥 𝟏 𝐢𝐬 𝐧𝐨𝐰 𝐟𝐮𝐥𝐥𝐲 𝐬𝐨𝐥𝐝 𝐨𝐮𝐭 𝐚𝐧𝐝 𝐜𝐥𝐨𝐬𝐞𝐝!⁣If you’re an AI engineer who can already prompt or fine-tune models but you’ve never been able to answer questions like: - Why is my 70B model using 120 GB of VRAM and still slow?- How do I serve 500 concurrent users on 4xH100s without going broke?- What actually happens inside FlashAttention / PagedAttention / tensor parallelism?- How do I save my company millions running open models in production?… then this is the course you’ve been waiting for.

From AI Engineer to AI Systems Engineer

Start small 

Learn to profile ruthlessly

Optimize step-by-step

Learning how to scale

Become an inference engine expert

Guest lectures by industry experts and professionals

We cannot teach you the basics of Python code.

You have shipped at least one non-trivial Python project

If you have never touched AI models, this course is not for you.

You can already load and run an LLM using HF Transformers

We can help with Docker and Kubernetes, don't worry.

Comfortable with basic terminal/SSH, git, yaml & json files

AI engineers, ML infrastructure engineers, and backend developers who own inference cost and need to 10–50× optimize it.

Founders &amp; engineers building LLM apps who are tired of burning money on OpenAI

AI engineers who don't understand system design for building reliable applicationsAnyone on job market for Inferencing/Solns Architect role

How to do Observability right?

ML Engineer with 10 years of experience in this field

A hands-on lab on observability for an agentic application and I'll show you how to use one OS tooling for all your team

Single tool for ML Engineers and Biz teams?

Far too many people think evals is all they need and no one taught them about what metrics to track for agentic pipeline

What's the difference between observability and evals

Most people spend time confused between libraries (Langfuse, Logfire etc) instead of tracing what metrics they need

Open source tools, not fancy libraries

How much will my model cost? Napkin Maths 101

Lead Research Engineer @ Abide

Most AI engineers in 2026 still have ZERO clue how much VRAM their model actually needs.

Quickly estimate model costs

Your RAG demo works on your MacBook. You think you’re ready for production. Then your 8×H100 box OOMs at 3am with 8users

Concurrency handling is never taught

5 numbers to look at when evaluating costs for real agentic workflows. Single-turn v/s multi-turn runs. How they differ?

Model math doesn't translate to Agentic Systems

What happens when you make an LLM call?

Understand the end‑to‑end journey from a user’s HTTP/API request down through inference engines, runtimes, and hardware

Run through the Full LLM Call Stack

We'll break down how prompts are tokenized, transformed, and processed, including core mechanics of prefill v/s decode

Let's dissect the Inference Process Step‑by‑Step

We'll do a case study diagnosing bottlenecks, choosing inference engines and reasoning for latency, throughput & scaling

Systems Level Thinking in Action

Whats next for AI Engineers?

If everyone knows how to do RAGs, and Agentic projects are failing, whats next?

Understand the Next Shift in AI Engineering

Knowing LangGraph, Pydantic, CrewAI, n8n is no longer enough.

Recognize Skill Gaps and Opportunities

Which core concepts from AI Architect Interview, Inference Engineering Interviews do I need to know

Key Concepts to stand out in your next interview

AI Careers in 2025+ : What No One's Telling You

ML Research Engineer, Book Author - LLMOps (O'Reilly), GPU Engg (Packt)

Understand what it really means to be an AI Engineer, LLMOps Engineer, Data Engineer, GPU Engineer/Solutions Architect

The 4 key roles emerging in LLMOps

Whether you’re from software, ML, hardware, or product—see where you fit in.

How to map your background to the right role

Learn what actually matters to land these roles in 2025+

How to position yourself without a PhD or FAANG badge

Get a no-fluff breakdown of the tools and stacks that matter in production- not just demos.

Learn directly from goabiaryan