AI Training Specialist — Stellar AI
Designed and refined training tasks to improve large language model reasoning and decision-making. Simulated user–AI interactions across diverse scenarios to guide model learning and alignment. Contributed structured feedback and safety-oriented task design to support reliability and performance. • Worked with real-world conversational and decision-making scenarios for training • Structured annotations and feedback loops to improve contextual accuracy • Focused on reliability, safety, and high-quality task formulation