AI Content Evaluator and Trust & Safety Specialist | Senior Frontend Developer

I evaluate and rank generative AI model responses for safety, instruction adherence, factual consistency, and reasoning quality using RLHF frameworks. I review complex prompts and multi-turn conversations for policy compliance, harmful content, and quality issues.

I conduct red-teaming and adversarial prompting to identify prompt injections, jailbreaks, implicit bias, and unsafe edge cases. I audit content for hate speech, self-harm, harassment, and confidential or PII disclosures.

I annotate coding, technical, and general-knowledge outputs in TypeScript, JavaScript, and HTML, validating syntax and functional correctness. I maintained a 99.2% quality compliance score across peer-review audits and quality-control checks.

I architect and build modular, responsive web applications using React, Next.js, TypeScript, JavaScript, and Tailwind CSS. My work includes dashboard trackers, e-commerce platforms, content templates, and interfaces with real-time UI updates.

I implement REST API integrations, dynamic search and filtering, asynchronous state management, and error handling to create reliable user experiences. I maintain clean, documented GitHub codebases and manage continuous deployments through Vercel and Netlify.

Featured work includes Thundey Track, an application and workflow tracker; an online bookstore platform; Royalty Parfait, a food-ordering web application; and a store and publishing blog template.

Completed a Bachelor of Science degree in Physics (Electronics), developing a rigorous foundation in analytical problem-solving, digital logic, systems theory, and mathematical modeling.