Mid-Level AI Evaluation Specialist
Open to offersNew to PlatformMaria Isabelle M. is an experienced AI Evaluation Specialist based in Lipa City, Batangas, Philippines, with a specialization in production-level LLM and multimodal evaluation. She excels in areas such as hallucination detection, reasoning analysis, and pre-acceptance dataset quality control, where she consistently processes 20–25 QA tasks daily under strict audit thresholds. Previously serving as an Analyst in the AI/LLM Evaluation Practice at Innodata Knowledge Services Inc., Maria ensured dataset integrity by reviewing conversational AI outputs and complex visual datasets, highlighting her proficiency in Conversational AI Evaluation and Multimodal Annotation QA. Her contributions include reducing spatial inconsistency risks and escalating critical evaluation failures to prevent downstream error propagation. With a strong foundation in QA governance from her tenure at Vanguard Screening Solutions and Accenture, Maria has significantly impacted workflow consistency and error prevention, showcasing her expertise in QA Operations & Risk Control.