LLM Fine-Tuning, LoRA, and Alignment Workflows

During my research scientist internship with the Chief Data Office at AT&T, I delivered this invited technical seminar for over 250 enterprise engineers and technical leaders. The seminar covered practical workflows for foundation model adaptation, Parameter-Efficient Fine-Tuning (LoRA / QLoRA), Supervised Fine-Tuning (SFT) out-of-distribution dynamics, RLHF/GRPO alignment paradigms, and establishing reproducible evaluation benchmarks for domain-specialized LLMs.

Aug 12, 2026 2:00 PM

AT&T Enterprise AI Technical Seminar