LLM Post Training Intern
TextRLHF
As a LLM Post Training Intern at Ethara AI, I contributed to the fine-tuning of large language models using SFT, RLHF, and RLVR techniques. My responsibilities included monitoring and evaluating response quality through standardized procedures, ensuring alignment with project goals. I participated directly in enhancing model outputs for accuracy, coherence, and safety.
• Performed response assessment and quality control using defined AI training protocols.
• Leveraged reinforcement learning from human feedback to optimize model performance.
• Collaborated with AI engineers to identify gaps and propose improvements in training data.
• Contributed to training documentation and process enhancement for future interns.
As a LLM Post Training Intern at Ethara AI, I contributed to the fine-tuning of large language models using SFT, RLHF, and RLVR techniques. My responsibilities included monitoring and evaluating response quality through standardized procedures, ensuring alignment with project goals. I participated directly in enhancing model outputs for accuracy, coherence, and safety. • Performed response assessment and quality control using defined AI training protocols. • Leveraged reinforcement learning from human feedback to optimize model performance. • Collaborated with AI engineers to identify gaps and propose improvements in training data. • Contributed to training documentation and process enhancement for future interns.
2026 - Present