Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
Appen
Data Annotation Tech
Telus
Image
Audio
Video
Evaluation/Rating
Classification
SegmentationWith experience across multiple AI evaluation platforms including Handshake AI, Multimango, and Atlas Capture, I have evaluated and labelled diverse data modalities spanning images, video, text, search results and audio. My work includes extensive R2I ELO image evaluation using structured multi-dimension rubrics covering instruction following, person ID preservation, visual quality, and artifact detection, as well as LLM output review assessing AI responses for accuracy, helpfulness, and safety. What sets me apart is the combination of deep rubric discipline and an ML engineering background that allows me to evaluate AI outputs with genuine technical insight rather than surface level review. I understand the reason behind annotation guidelines — from calibrating tie verdicts and avoiding tie-maxxing, to grounding every judgment in clearly visible evidence without hallucination. This, paired with experience fine tuning BERT models and building production ML systems, makes me both a rigorous evaluator and someone who understands how labelled data directly impacts model quality.
ImageEvaluation/RatingEvaluated 100+ AI-generated image pairs across a 6-dimension headline: Overall Preference, Instruction Following, Person ID Preservation, Reference Preservation, Visual Quality, and Absence of AI Artifacts. Grounded all verdicts in clearly visible image details, avoided tie-maxxing, and produced character-constrained open feedback per task. Platforms: Handshake AI, Multimango.
Bachelor of Science (EDU), Education
Social Media Manager
