Kalman AI Lab · SLM Builders Program

Build a language model from scratch. Deploy it as an agent.

A free, self-paced 8-week program for engineers who want to go from writing their first autograd engine to shipping a deployed, aligned small language model operating as an agent. No prerequisites beyond Python.

Express interest →Start reading now
CostFreeDuration8 weeks (+ optional research month)FormatSelf-paced · Bi-weekly live Q&A
§ 01 · The arc

Not a model you API-called. One you built.

Most AI education teaches you to use models. This program teaches you to build them — from the autograd engine up through the full transformer, then training, aligning, and wrapping the result in an agent system that runs in the real world.

By Week 8, you'll have a working, deployed multi-agent orchestrator — connected to external tools via MCP, running your own SLM as one of its agents.


Part 1
Weeks 1–5 · AI Building Blocks, LLMs & Fine-Tuning
Part 2
Weeks 6–8 · Agents, MCP & Orchestration
Optional
Weeks 9–12 · Research month (your choice of track)
§ 02 · The journey

Eight weeks. Eight things you ship.

Every week ends with something you built. The deliverables accumulate — your tokenizer feeds your training run, your model feeds your agent, your agent becomes your capstone.

Part 1 — AI Building Blocks
Week 01

Your first neural engine

You'll understand what a gradient actually is, not just how to call .backward(). Mixed precision, checkpointing — the real fundamentals.

A working autograd engine and BF16 training loop — written by you.
Week 02

Build GPT-2 from scratch

Tokenization, positional encodings, self-attention, the full transformer block. You'll never treat a model as a black box again.

A GPT-2 that produces correct logits — verified against the reference.
Week 03

Make it modern

Every upgrade used in today's frontier models — RoPE, RMSNorm, SwiGLU, grouped-query attention, mixture of experts. Plus: how vision plugs into the same architecture.

A GPT-2 upgraded with RoPE, SwiGLU, GQA and a working MoE layer.
Week 04

Feed it good data

A model is only as good as its data. You'll train a tokenizer, filter noisy web text, deduplicate at scale, and generate synthetic data.

A custom BPE tokenizer and a filtered, deduplicated pretraining corpus.
Week 05

Train, scale and align

Scaling laws, multi-GPU training, experiment tracking — then making the model actually useful via instruction tuning and preference learning.

A compute-optimal training run + a checkpoint fine-tuned with SFT and DPO.
Part 2 — Agents & Orchestration
Week 06

Connect it to the world

The Model Context Protocol is how models talk to external systems. You'll build the server, define tools and resources, and wire your model to it.

A working MCP server exposing tools and data — connected to your SLM.
Week 07

Give it agency

ReAct-style loops, planning, memory, when to use one agent vs. many. Your model starts making decisions.

A single tool-using agent that reasons, acts and checks its own work.
Week 08

Ship it

Orchestration patterns, supervisor/worker routing, failure handling — then putting it all together into a system that runs in the real world.

A deployed multi-agent orchestrator running your own SLM. Live demo day.
§ 03 · Resources · Start today

You don't need to wait to begin.

These are the materials, tools and compute options we recommend before Week 1. Everything here is free.

Start here
Go deeper
Free compute
§ 04 · Optional research month

Where do you want to go next?

After the core 8 weeks, choose one track to go deep on for a focused fourth month. All three connect directly to Kalman AI's own research roadmap.

Track A

Autoresearch

Multi-modal research agents for regulated data.

Build agents that work across radiology, genomics, clinical records, and scientific literature — with the compliance architecture each domain requires.

Best if you're drawn to healthcare, life sciences, or regulated data.
Track B

World Models

Prediction, planning and active inference.

Train a predictive world model, implement active inference, and build a planning loop on top. The principled complement to LLM-heavy stacks.

Best if you want to go deep on how intelligence actually works.
Track C

Vision-Language Models

Extend your SLM into vision.

Vision encoders, CLIP-style contrastive training, projector-based fusion, multimodal instruction tuning — then deploying a VLM that answers questions grounded in images.

Best if you want your model to see, not just read.
§ 05 · Questions

Is this for me?

The program is for engineers who want to go beyond using LLMs to actually building, training, aligning, and deploying them. Comfort with Python is assumed. Everything else we build from scratch.

  1. Do I need a deep learning background?

    No. Comfort with Python is all we assume. The program builds the theory from scratch — you'll understand why things work, not just how to call them.

  2. How much time does each week take?

    Around 8–12 hours: a pre-reading session, the core lab, and cleaning up your deliverable. It's self-paced, so stretch it across two weeks if needed.

  3. Do I need a GPU?

    Weeks 1–4 run fine on free Colab or Kaggle tiers. From Week 5 (multi-GPU training) onward, you'll want paid GPU time — Lambda Cloud is the most cost-effective option.

  4. Can I skip weeks?

    Each week's deliverable is the input to the next — your tokenizer feeds your training run, your model feeds your agent, your agent becomes your capstone. Skipping is possible, but you'll feel the gaps.

  5. Is there any support?

    A live Q&A runs every two weeks, open to everyone regardless of where they are in the sequence. Bring questions on any week, your labs, or your capstone build.

  6. Is the research month compulsory?

    No. Weeks 1–8 are a complete, self-contained program ending in a deployed capstone. The research month is for anyone who wants to go further in one specific direction.

  7. What do I walk away with?

    A working, aligned SLM you trained yourself, wrapped in an MCP-connected agent orchestrator you built — plus, if you take the research month, a focused project in your chosen track.

Ready to build

Express interest or just start reading.

The program is free and self-paced. Drop us a line to be notified when the next cohort opens, or scroll back up and start with the resources today.

contactus@kalman.in →Start reading now