MasterLLM▌Engineering.
A 4-week intensive from transformer internals and KV cache to production deployment on edge devices. Taught by Dr. Raj Dandekar (MIT PhD) with 8 industry experts from the world's top AI companies.
Two phases.
One complete education.
15 lectures across 4 weeks. Each phase is self-contained — take one or both.
Apr 20 – May 3, 2026
May 4 – May 18, 2026
Built for engineers
who want to go deep.
Engineers transitioning into ML infrastructure or AI engineering
Students targeting roles at Anthropic, NVIDIA, Microsoft, Apple, Amazon
Engineers who want to go beyond using LLMs — to building inference systems
Researchers who need production engineering depth alongside theory
Leave
interview-ready.
Top-company interview question:
"Design a low-latency, high-throughput LLM inference system handling millions of requests. Walk me through the engineering trade-offs."
Asked at Anthropic, NVIDIA, Microsoft, Meta, Google DeepMind. You will have a complete answer.
Answer end-to-end inference system design questions in any ML interview
Explain low-latency, high-throughput, cost-optimised LLM serving at scale
Deploy real LLMs on Mac Mini, Raspberry Pi 5, Android & Jetson Orin Nano
Build industry-level portfolio projects from 4 hardware lab days
Get career insights directly from engineers at Anthropic, NVIDIA & Microsoft
Learn from engineers
at the frontier.
9 industry experts from Anthropic, NVIDIA, Microsoft, Apple, AnyScale, Red Hat, Amazon and Mastercard. Sessions at Anthropic, NVIDIA, Microsoft and Apple include a dedicated career insights segment.
Don't just learn it.
Run it on real hardware.
4 dedicated lab days. Every device has a different bottleneck — and you'll benchmark each one live.
Mac Mini
Set up llama.cpp, run your first inference, benchmark tok/s across model sizes.
Raspberry Pi 5
Quantization experiments on ARM. Compare INT4 vs INT8 latency. Power-aware inference.
Android Device
SmolChat-Android live session with Shubham Panchal. Deploy a real LLM on your phone.
Jetson Orin Nano
CUDA inference on edge GPU. TensorRT-LLM on Jetson. GPU vs CPU throughput battle.
Lab Day 3 (Android · Shubham Panchal) is a confirmed 3-hour workshop. All other labs conducted by Dr. Raj Dandekar.
Order everything together — save on shipping & customs
Students frequently ask us to list all required hardware upfront so they can order in a single shipment and avoid separate delivery and customs fees. Here is the complete list. Purchase your hardware before the first lab session (Lab Day 1 · Apr 25).
Raspberry Pi 5
RequiredRequired · 4GB or 8GB RAM
Used in Lab Day 2 for ARM inference and quantization experiments. The 4GB model is sufficient.
Jetson Orin Nano
RequiredRequired · 8GB recommended
Used in Lab Day 4 for CUDA inference and TensorRT-LLM. The 8GB Developer Kit is the cheapest model that can comfortably run LLM projects.
Mac Mini (M4)
OptionalOptional — can use your own PC
Lab Day 1 is designed for Mac Mini (Apple Silicon). If you don't have one, you can run the same llama.cpp and benchmarking exercises on your own laptop or PC.
Android Phone
RequiredRequired · Any Android 10+
Lab Day 3 with Shubham Panchal. Any Android 10+ phone with at least 6GB RAM works. You almost certainly already own one.
You likely already own this
Hardware is not included in the workshop fee. The Hardware Lab Sessions add-on covers instruction and lab access only. Prices and availability vary by region.
Choose your workshop.
Select what you need. Everything adjusts instantly.
Step 1 — Choose your base
Foundations & Optimization
Apr 20 – May 3, 2026 · 8 lectures
₹45,000
Production & Edge Deployment
May 4 – May 18, 2026 · 7 lectures
₹55,000
Step 2 — Add-ons (optional)
Guest Speaker Pass
All 9 sessions — Anthropic, NVIDIA, Microsoft, Apple, AnyScale, Red Hat, Amazon, Mastercard
+₹30,000
Hardware Lab Sessions
4 guided lab days — Mac Mini, Raspberry Pi 5, Android, Jetson Orin Nano. Hardware must be purchased separately; this pass covers lab access and instruction.
+₹30,000
Research Roadmap + Code Starter
Personalised roadmap PDF + starter code template for your research project
+₹15,000
1:1 Research Mentorship — 2 Months
with Yash Dixit, AI/ML Product Manager at Apple · 4 bi-weekly sessions
+₹70,000
Dr. Raj Dandekar
MIT PhD · Vizuara AI Labs
Dr. Raj Dandekar
MIT PhD · Co-founder & Director, Vizuara AI Labs
Dr. Raj holds a PhD from MIT and is the co-founder and director of Vizuara AI Labs. He has built a 50,000+ subscriber YouTube channel dedicated to teaching LLMs from first principles, and has taught 200+ engineers across previous workshop cohorts.
His teaching philosophy: visual intuition first, mathematical rigour second, hands-on implementation always. Every concept is taught from scratch — no hand-waving.
Common questions.
About the Workshop
Hardware
Guest Speakers