LLM Post Training Intern — Ethara AI
Performed LLM post-training work focused on RLHF and Supervised Fine-Tuning (SFT) to improve AI response quality. Evaluated AI-generated outputs for accuracy, relevance, consistency, and safety as part of an iterative quality-improvement loop. Supported prompt analysis and data annotation activities to prepare training and evaluation datasets for production use. • RLHF-based post-training and SFT support • Accuracy, relevance, consistency, and safety evaluation of model outputs • Prompt analysis and model evaluation for production systems • Assisted with data annotation to support training workflows