Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
Computer Code Programming
Evaluation/Rating
Question Answering
Prompt + Response Writing (SFT)I have been working as an AI Behavioral Evaluation Engineer – Architecture and Strategy at Revelo, where I help evaluate and improve AI model responses. My work includes comparing different outputs, checking if they follow instructions correctly, testing reasoning and accuracy, and writing feedback to help make the models better. I also work with prompt evaluation, response ranking, and quality review while following detailed project guidelines. Besides my AI evaluation experience, I also have a software engineering background, so I can understand technical topics and coding tasks well. I have experience with JavaScript, TypeScript, Node.js, React, Next.js, and databases. I pay close attention to details, enjoy solving problems, and always try to provide consistent and high-quality work. I believe these skills help me contribute effectively to AI training and data annotation projects.
Audio
Fine-tuningWorked on AI training and data annotation projects involving the Amharic language. Reviewed and labeled text data, evaluated AI-generated content for quality and accuracy, and followed detailed annotation guidelines to ensure consistent results. Helped improve AI language models by providing high-quality annotations, identifying errors, and making judgments based on linguistic and cultural knowledge of Amharic.
Computer Code ProgrammingEvaluation/RatingI evaluate AI-generated responses and compare different model outputs to improve quality and accuracy. My work includes reviewing coding and reasoning tasks, following annotation guidelines, identifying errors, and providing clear feedback and justifications. I also help ensure AI models produce reliable, helpful, and consistent responses across different scenarios.
Electrical and Computer Engineering, STEM
Job Title: AI Behavioral Evaluation Expert – Architecture and Strategy Company: Revelo I evaluate AI-generated response
