At Meta, I evaluated generative AI products using structured prompt evaluation, rubric-based scoring, and human feedback. I diagnosed hallucinations, reasoning errors, and inconsistent outputs, then shared prioritized findings with engineering and product teams.
At Appen, I analyzed LLM output datasets and built evaluation methodologies that reduced assessment time and improved scoring consistency. At Scale AI, I led a distributed team of 70+ AI evaluators and handled onboarding, training, quality calibration, and performance management.
I also built AI and IoT projects, including a computer vision study assistant using Python, Flask, Google Cloud Vision API, and Raspberry Pi. My work draws on a B.S. in Computer Engineering and hands-on experience with Python, SQL, REST APIs, and Git.
