Angelique B.

Hi, I'm Angélique, a bilingual (French/English) linguist with a Master's in Applied Linguistics and over 4 years working inside AI teams, including Cisco Webex, Promethean AI, and most recently an LLM evaluation and conversation design role at an AI startup. I help AI and NLP teams catch what automated pipelines miss: tone that's off, prompts that underperform, outputs that don't hold up across languages or cultures. Here's where I typically plug in: LLM Output Evaluation & Prompt Refinement: I assess AI responses for accuracy, safety, tone, and instruction-following, identify recurring failure modes, and refine prompts to fix them at the source rather than patching outputs one by one. Conversational AI & Chatbot Review: I review dialogue flows and chatbot responses for clarity, grammatical accuracy, and cultural fit, the details that make the difference between a bot that sounds functional and one that sounds right. Multilingual & Cross-Language Consistency: I design and QA prompts across French and English, and work on translation/localization consistency so your product doesn't lose nuance (or accuracy) when it crosses languages. Data Annotation, Extraction & Terminology Management: I label and structure data for ML training, and build glossaries and terminology systems that keep your outputs consistent across a whole product line, not just one feature. I'm also an avid reader who loves getting lost in books and research, digging into different sources, fact-checking, and proofreading. I genuinely enjoy the process of exploring a topic in depth, connecting ideas, and making sure every detail is accurate. If you're training a model, shipping a chatbot, or trying to figure out why your AI sounds fine in English but off in French, I'd be glad to help you get it right.