ProgramsDeep Learning with LLM
The engineer path · AI cluster

Deep Learning with LLM

Build the models, don't just call them. Backpropagation from scratch, CNNs, transformers written by hand, LLM fine-tuning and diffusion pipelines — with the mathematics underneath, not around it.

4 levels
L0 → L3
3 → 120 hrs
Per level
PyTorch · HuggingFace
Mastery stack
Cloud GPU
No GPU needed
§ 01Choose your level

Four rungs. Start where you are, finish at Mastery.

Sessions are always 2 hours. The hours are fixed; the calendar flexes — the same level runs daily, alternate-day, or as a summer intensive. Prices shown are student prices; professional pricing is on the pricing page.

L0Discover
3 hours · one sitting, a single day

What deep learning actually is

Watch a neural network learn in front of you, and see plainly where the magic stops and the mathematics starts. A single afternoon, no cost.

L1Foundation
12 hours · 6 sessions · about 1 week

Neural-network foundations

Perceptrons to a working multi-layer network you train yourself — activations, loss, gradient descent, and why training goes wrong.

L2Practitioner
40 hours · 20 sessions · about 1 month

CNNs, RNNs — computer vision and NLP

Convolutional and sequence models applied to real vision and language tasks, with a trained model and honest evaluation to show for it.

L3Mastery
120 hours · 60 sessions · about 3 months

Transformers, LLMs and diffusion

Self-attention from scratch, LLM fine-tuning with LoRA, RAG, evals, Stable Diffusion and serving at production scale. Full syllabus below.

Not sure between this and Data Science? They are a staircase, not a fork. Data Science with AIML is the analyst path and the natural entry point; this stream sits above it for people who want to build and train the models themselves. If you want to ship products using existing models instead, go to Vibe Producting.
§ 02L0–L2 · published syllabus

What the levels below Mastery cover

Our ladder is a spiral, not a straight line. L0 and L1 are outcome-first: you make something impressive on the first day and no theory gets in the way. L2 is where the foundations genuinely begin. L3 then deliberately re-covers 60–70% of L2 at real depth before going past it — the overlap is a feature, not repetition. You earn the "why" only once you are invested in the "what".

L0 · 3 HRS
Curiosity

A demo and a guided first build. No theory at all — just a win you can point at.

L1 · 12 HRS
Confidence

Bigger builds, same spirit. Concepts appear only where a build actually needs them.

L2 · 40 HRS
Foundations begin

The first real grounding in how and why — taught applied, ending in a project.

L3 · 120 HRS
Depth

Re-covers L2's foundations at full depth, then goes well beyond into advanced work.

L0 · Discover · 3 hours · free

"I ran real AI models — today."

See it: A neural net recognizing images, an LLM holding a conversation, and an AI generating images from words.

Make it, guided: Run a pretrained model in a notebook — classify your own photo, generate text and an image, and watch a model "see" and "write".

Runs on Colab with a free GPU — nothing to install. No assessment.

L1 · Foundation · 12 hours · 6 sessions

Six sessions, six things you built

  1. See a model "see" — image classification on your own photos (pretrained)
  2. Teach a model — train a tiny image classifier, guided
  3. Language AI — sentiment and summarization with a transformer pipeline
  4. Generate — make images with a diffusion model via a UI or notebook
  5. Wrap it — a mini demo app (Gradio) around a model
  6. Your own mini AI demo, plus a showcase

You leave with a shareable AI demo. Assessed on completion and the showcase.

L2 · Practitioner — 40 hours, where the foundations begin

The first real grounding — how neural networks actually work in PyTorch, CNNs for vision, basic NLP, and applied transformers and LLMs.

UnitWhat you learn and buildSessionsHours
U1 · Python & Math Intuition for DLTensors, an intuition for gradients, PyTorch basics36
U2 · Neural NetworksPerceptron to MLP, activations, a training loop written in PyTorch48
U3 · Computer Vision with CNNsConvolutions, image classification, transfer learning48
U4 · NLP & SequencesText and embeddings, RNN/LSTM basics, sentiment36
U5 · Using Transformers & LLMsHugging Face pipelines, applied transformer and LLM use36
U6 · Practitioner ProjectBuild and demo a deep-learning model — vision or text36
Total2040

Project: A working deep-learning model — an image classifier, a text model, or a small generative demo — presented.

Tools: PyTorch · torchvision · Hugging Face · OpenCV · Gradio · Colab GPU · Git.

Assessment: Continuous labs 40% · unit checkpoints 20% · project 40%.

Overlap into L3: U1–U5 are the foundations L3 deepens — it adds DL maths and backprop rigour, transformers written from scratch, LLM fine-tuning with RAG and evals, diffusion, multimodal and speech, alignment, deployment and a capstone.

§ 03L3 · Mastery · published syllabus

120 hours, unit by unit

This is the complete Mastery syllabus — the ceiling of the stream, and what every level below builds toward.

What you can do at the end

The outcome

You can build, train, fine-tune, evaluate and deploy modern deep-learning systems — CNNs for vision, sequence models, transformers, LLM applications with fine-tuning and RAG, and diffusion pipelines — with a rigorous grasp of the mathematics underneath.

Format

How it runs

120 hours · 60 sessions × 2 hours · about 3 months. Prerequisite: Data Science L2/L3 or a placement check — you should be comfortable with Python and ML basics. GPU-heavy labs run on cloud GPU, so no local GPU is required.

Tools & environment

PyTorchtorchvisionHugging Face TransformersDatasets / Tokenizers / PEFTdiffusersComfyUILangChain / LlamaIndexFAISS / ChromaOpenCVvLLMFastAPIDockerCloud GPU (e.g. RunPod)Git

Deliberate stack choice: PyTorch throughout, not TensorFlow — it is what research and most production teams actually use.

UnitWhat you learn and buildSessionsHours
U1 · Mathematics for DLLinear algebra for deep learning · gradients, chain rule, backpropagation · optimization (SGD, momentum, Adam), learning-rate schedules · loss functions · probability and information theory — entropy, cross-entropy, KL48
U2 · Neural Networks & PyTorchPerceptron to MLP · activations · backprop written from scratch · PyTorch tensors and autograd · training loops, datasets and dataloaders · regularization (dropout, batch/layer norm), weight init · debugging training runs612
U3 · CNNs & Computer VisionConvolutions, pooling, feature maps · architectures from LeNet to ResNet and EfficientNet · image classification · transfer learning · object detection with YOLO, segmentation intro · data augmentation · OpenCV integration612
U4 · Sequence ModelsSequential data · RNN, LSTM, GRU · vanishing gradients · time-series forecasting · seq2seq · attention intuition as the bridge to transformers510
U5 · Natural Language ProcessingText preprocessing and tokenization · embeddings (Word2Vec, GloVe, FastText) · neural NLP for classification, NER and summarization · topic modeling · evaluating NLP systems510
U6 · TransformersSelf-attention from scratch, multi-head attention · positional encoding, residuals and layer norm · encoder-only (BERT), decoder-only (GPT), encoder-decoder (T5) · tokenization (BPE, WordPiece) · pretraining objectives · Hugging Face Transformers612
U7 · Large Language ModelsThe LLM landscape and scaling laws · prompt engineering · fine-tuning — full versus PEFT/LoRA · quantization (FP16/INT8, GGUF) · RAG with embeddings, vector DBs and chunking · agents, tool use and function calling · evals — perplexity, benchmarks, human eval, hallucination · RLHF concept · responsible AI, bias, prompt injection612
U8 · Generative Image AIGANs versus VAEs versus diffusion · forward and reverse process, noise schedules · U-Net and latent diffusion · CLIP text conditioning · samplers (DDIM, Euler, DPM++) · img2img, inpainting, ControlNet · ComfyUI node workflows510
U9 · Fine-tuning & DeploymentLoRA for LLMs and diffusion — dataset prep, captioning, rank and alpha · quantization and optimization · serving with vLLM and FastAPI wrappers · Docker · cloud and serverless GPU · monitoring, cost and API security48
U10 · Multimodal & Speech AIVision-language models (CLIP, LLaVA) · combined image-and-text tasks · speech — ASR with Whisper and TTS · audio deep-learning basics510
U11 · Advanced Generative & AlignmentGANs and VAEs in depth · advanced diffusion · RLHF and DPO for preference alignment · distillation and efficiency510
U12 · CapstoneScope → build or fine-tune → evaluate → deploy → present a live demo36
Total60120

The capstone

Choose one track and take it end to end, deployed with a live demo:

(a) An applied CV system — detection or segmentation trained in PyTorch and served as an API. (b) An LLM application — a fine-tuned or RAG-based assistant with citations and an eval harness. (c) A generative pipeline — a custom LoRA plus ControlNet and ComfyUI workflow, packaged and reproducible.

You deliver: a deployed system, a repository, an evaluation report and a live demo.

How you're assessed

Continuous lab work25%
Unit projects (4)25%
Capstone (rubric)40%
Presentation & viva10%

Syllabus is a working draft — hours per unit are indicative and validated by the practitioner who teaches the stream. Reinforcement learning appears only as the RLHF concept in U7; a full RL module is out of scope.

§ 06Practitioner-instructors

Who will teach you

Every instructor is currently building in the field they teach — and is certified on our level template before taking a cohort alone. Subject expertise is the entry ticket, not the job.

Practitioners, not lecturers

Every instructor is currently building in the field they teach. If they stop practising, they stop teaching that stream.

Trained on our template

Subject knowledge is the entry ticket, not the job. Every instructor is certified on the CEFTA level template before they take a cohort alone.

Standardized delivery

The same module runs the same way in every centre and every partner campus. That consistency is the product.

Named instructor profiles go up as each cohort's trainer is confirmed — we publish people, not stock photographs. We're hiring practitioner-instructors →

Dates for Deep Learning with LLM

Tell me when the next batch opens

One email when a cohort is published for this stream. Nothing else, ever.

One email when a batch opens. No newsletter, no drip sequence, unsubscribe in one click.

Understand the models, don't just use them.

Start with the free 3-hour L0 Discover session — see a network learn, then decide whether to climb.