About Me
Available
NIPUN AGGARWAL
Trust & Safety · LLM Training · Content Moderation · Community Management
Started reviewing content at scale in 2019. Six years later, I adversarially test large language models - finding the gaps before bad actors do. I bring a rare combination: the instincts of someone who has reviewed thousands of real harmful cases, and the technical curiosity to understand how AI systems fail.
My background in psychology and history gives me an unusual lens - I think about why systems fail, not just how. I'm building toward AI Governance and Responsible AI.
Strengths
Critical Thinking
Assessing intent, context, and severity - not just surface content - before making a call.
Lateral Thinking
Finding edge cases others miss - whether probing model guardrails, evaluating output quality, or spotting patterns in annotation data.
Adaptability
From human content review to LLM training - the same core instincts applied across entirely new domains.
Team Player
Safety work is collaborative - escalations, policy decisions, and reporting all depend on clear cross-functional communication.
Intellectual Curiosity
Two degrees, three certifications, and a career that's deliberately evolved - always looking for the next layer of understanding.
Let's Connect
GET IN TOUCH
Open to remote roles in Trust & Safety, LLM Training, and AI Governance. If you're building safer AI, I'd like to help.