LLM engineer, not API caller

Go from using LLMs to understanding and shaping them: see the forward pass and the KV cache, fine-tune with LoRA/QLoRA on a free GPU, quantize and serve efficiently, and evaluate and secure what you ship. This is the line between "I call an API" and "I build LLMs." Builds on your BYO-7 tokenizer and BYO-8 mini-GPT.

🧠 Understandprose-first explainers
🎮 Drivebreak it in the browser
✍️ Checkquiz with why-feedback
🔨 Buildfine-tune, quantize, serve
🏗️ Applyjudgment drill
📋 Productionhow it bites in prod
0%

🏁 Phase capstone — your own fine-tuned, quantized, served, evaluated LLM

One end-to-end LLM-engineer portfolio piece: QLoRA fine-tune an open model on a domain dataset (security Q&A or finance) → quantize it to GGUF → serve it (Ollama/vLLM) → evaluate before/after with lm-eval-harness + an LLM-as-judge rubric → red-team it against the OWASP LLM Top-10 (BYO-16). One write-up ties it together — the standout "LLM engineer" resume item most candidates lack. Read a key paper (LoRA or DPO) with your 3-pass method. Ready for Phase 7 when you can explain a transformer end-to-end, and fine-tune + quantize + serve + evaluate + secure an open model.

Full guide: phase-6b-llm-indepth.md ↗

← Previous
Phase 6 · LLMs, RAG & Agents
Next →
Phase 7 · MLOps