Senior Reviewer / Contributor
Evaluation, RLHF, Rubrics related projects
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
I have extensive hands-on experience in data labeling and AI training—particularly in LLM evaluation, rubric creation, and fine-grained prompt/response analysis. My work spans multiple platforms, including DataAnnotation, Outlier where I handle complex tasks such as multi-turn conversation assessment, instruction-following checks, localization reviews, truthfulness verification, and safety/guardrail evaluations. A large part of my contribution involves writing atomic, self-contained, and unambiguous rubrics for model judging, as well as diagnosing issues in model reasoning, verbosity, and structural clarity. This experience has given me a strong sense of what distinguishes a merely acceptable model response from a genuinely excellent one. Beyond evaluation, I also work on prompt clarity improvement, scenario design, and edge-case testing to stress-test model behavior. My background in architecture, BIM, and cross-disciplinary documentation gives me an unusual advantage: I can read highly technical content, extract the logical structure, and translate it into precise, human-sounding criteria for RLHF pipelines. I am meticulous, consistent, and comfortable handling large volumes of nuanced judgment calls. Overall, these experiences strengthen my ability to produce reliable, high-quality training data that directly improves model reasoning and user experience.
Evaluation, RLHF, Rubrics related projects
Vison SFT related projects
Create BIM model from the AI generated plans and review the feasibility
RLHF, prompt writing and review, evaluation of response, text detection and review, audio review
Bachelor of Arts in Architectural Studies, Architectural Studies
Master of Architecture, Architecture
Head of BIM
Architect / Project Manager / Technical Writer