Code reviewer
Review and evaluate prompts and code generated output by LLM's, correcting them and providing the correct response
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
I have hands-on experience in AI training and data labelling, with a focus on model alignment, annotation quality, and workflow optimisation. At Outlier AI, I contributed to improving model safety and reasoning accuracy using reinforcement learning from human feedback (RLHF) pipelines. I designed structured prompts for classification, reasoning, and conversational tasks, while auditing large-scale annotation pipelines to enhance data quality and consistency. This work gave me expertise in identifying inefficiencies, debugging annotation workflows, and surfacing actionable insights that directly improved LLM explainability and robustness. In addition to annotation and model evaluation, I bring a strong technical foundation from my work as a Machine Learning Engineer and Solutions Architect, where I built automated model evaluation pipelines, deployed enterprise-grade APIs, and streamlined ETL data processes. This combination of AI training data expertise and engineering skill allows me to contribute not only to high-quality labelling and evaluation, but also to the design of scalable workflows that bridge the gap between raw data, AI models, and real-world applications.
Review and evaluate prompts and code generated output by LLM's, correcting them and providing the correct response
Bachelor of Science, Computer Science
Solutions Architect
Machine Learning Engineer