Chivas Prompts
Created and refined prompts and ideal responses for AI systems. Designed tasks to evaluate model capabilities and improve instruction following, reasoning, and coding performance.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
I have experience working on AI training and data annotation projects with companies such as Outlier, Scale AI, and xAI. My work has included evaluating and improving AI-generated responses, creating and reviewing prompts, ranking model outputs, performing quality assurance tasks, and contributing to coding-focused AI training projects. I have worked on multiple projects involving large language models, following detailed guidelines to ensure accuracy, consistency, and high-quality training data. Through these experiences, I have developed strong analytical, problem-solving, and attention-to-detail skills while helping improve the performance and reliability of AI systems. For the project section, you could add: * Apron Evals – AI response evaluation and quality assessment * Hopper V2 – Model output ranking and comparison * Chivas Prompts – Prompt creation and refinement * Chivas MT – Coding prompt and response evaluation * Additional AI training projects with Scale AI and xAI involving data annotation, model evaluation, prompt engineering, and quality assurance.
Created and refined prompts and ideal responses for AI systems. Designed tasks to evaluate model capabilities and improve instruction following, reasoning, and coding performance.
Evaluated and ranked AI-generated responses based on accuracy, reasoning, helpfulness, and instruction adherence. Provided detailed feedback to improve model performance and contributed to RLHF workflows for large language model training.
Bachelors, Business Administration
Data Labelling Specialist
Ai Tutor