Technical Blog Series: Causal ML & LLM Fine-Tuning

Ordered deep-dive series for ML engineers: causal inference (SCM, IPS) and production LLM fine-tuning (SFT, LoRA, QLoRA, DPO, multi-adapter).

SERIES · 2 PARTS

Causal Machine Learning: Prediction to Intervention

Structural causal models, backdoor adjustment, and IPS for production decision systems.

  • P01Why Machine Learning Demands Causal Inference
  • P02Fixing Selection Bias in Enterprise Data with Inverse Propensity Scoring (IPS)
Open series
Causal Machine Learning: Prediction to Intervention

SERIES · 5 PARTS

Model Fine-Tuning: SFT, LoRA, QLoRA & DPO

End-to-end LLM adaptation: PEFT, QLoRA, preference alignment, and multi-adapter serving.

  • P01The Definitive Guide to LLM Fine-Tuning: Objectivee, Mechanisms, and Hardware
  • P02Deconstructing LoRA: The Math and Mechanics of Low-Rank Adaptation
  • P03A Technical Guide to QLoRA and Memory-Efficient Fine-Tuning
  • P04Aligning LLMs with Direct Preference Optimization (DPO)
  • P05Building LoRA Multi-Adapter Inference on AWS SageMaker
Open series
Model Fine-Tuning: SFT, LoRA, QLoRA & DPO

Shipping AI Systems?

I help teams design and deploy scalable ML / RAG / LLM pipelines and MLOps infrastructure.



Or explore: