Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
LabelboxNo subject matter listed
Computer Code ProgrammingI am an AI evaluation specialist and engineering physicist with hands-on experience in data annotation, adversarial red teaming, and systematic benchmarking of large language models (LLMs). My work involves generating and annotating complex adversarial prompts to uncover vulnerabilities, classifying outputs using structured safety taxonomies, and building reproducible datasets to support engineering teams in patching systemic risks. I have conducted cross-lingual evaluations in both English and Hindi, identifying language-specific safety gaps invisible to monolingual teams. My technical toolkit includes Python, n8n, Apify for web scraping, and full-stack development with React, Supabase, and Appwrite. I have published automation tools to Apify’s marketplace and engineered LLM benchmarking pipelines, demonstrating a strong ability to design, test, and document robust data workflows for AI training and evaluation. My background in engineering physics ensures a rigorous, hypothesis-driven approach to annotation, risk analysis, and structured reporting.
I was working on a project named Agent as a world , we need to tune rubrics and check LLM fails or pass. I also done ATC transcription on Labelbox
Bachelor of Technology, Engineering Physics
AI Developer and Automation Specialist
