Fine-tuning & Model Evaluation
LoRA / QLoRA, instruction tuning, preference data, and building evaluation suites you can trust before you ship.
🎯 Who it's for
Engineers comfortable with LLM applications who need to customise models and prove they got better.
✅ Prerequisites
- LLM Application Engineering or equivalent
- PyTorch basics
- Comfort with the training loop
- GPU access — provided in the lab
Topics covered
- When to fine-tune, and when not to
- LoRA and QLoRA
- Instruction and preference tuning
- Building evaluation suites
- LLM-as-judge and its pitfalls
- Regression testing and release gates
Expected completion timeline
7 weeks part-time at 8–12 hours per week ≈ 1.6 months. Self-paced learners can go faster; the live cohort keeps this pace.
Data and method
You produce: A curated tuning dataset and a baseline evaluation.
Fine-tune and compare
You produce: A LoRA-tuned model that beats the baseline on your evaluation.
Evaluation harness and capstone
You produce: A reusable evaluation suite and a written analysis of the trade-offs.
🧭 Where this fits
Advances the LLM / Generative-AI Engineer path toward senior roles. See the career & salary map for the full path, the expected pay by region, and the total cost.
💳 Delivery & fees
Available in all four delivery formats. Fees vary by format and are confirmed on your advisor call; instalments available.
Add this to your plan
Book a call and we'll place this course in a full path toward the role you want.
Talk to an advisor