At TELUS DIGITAL, I evaluate AI and LLM outputs for accuracy, relevance, safety, and adherence to project quality guidelines. I handle 1,500+ monthly rating tasks across classification and multimodal pipelines.
At DA.TECH, I configure generative AI prompt workflows and evaluate text and multimodal outputs against client guidelines. I also document error taxonomies and write technical rationales for ratings on complex edge cases.
At VERBATIM ADVISORY GROUP LLC, I evaluated degraded audio, including accents, crosstalk, and background noise, while maintaining 99% verbatim accuracy. I also followed confidentiality, secure file-handling, and client compliance standards.
