LLM Post Training Intern — Ethara AI
Text
As an LLM Post Training Intern at Ethara AI, I evaluated and annotated AI-generated chatbot responses for helpfulness, accuracy, and safety. I identified hallucinations, factual errors, and bias patterns, providing structured feedback to improve model quality. I worked extensively with RLHF-adjacent data annotation and response ranking processes under the mentorship of Quality Leads.
• Evaluated 200+ LLM responses per week across various topics
• Documented issues such as hallucinations and awkward phrasing to aid post-training
• Applied adversarial and edge-case prompts to uncover AI limitations
• Maintained a 98%+ task completion rate with on-time delivery
As an LLM Post Training Intern at Ethara AI, I evaluated and annotated AI-generated chatbot responses for helpfulness, accuracy, and safety. I identified hallucinations, factual errors, and bias patterns, providing structured feedback to improve model quality. I worked extensively with RLHF-adjacent data annotation and response ranking processes under the mentorship of Quality Leads. • Evaluated 200+ LLM responses per week across various topics • Documented issues such as hallucinations and awkward phrasing to aid post-training • Applied adversarial and edge-case prompts to uncover AI limitations • Maintained a 98%+ task completion rate with on-time delivery
2025 - 2025