Technical AI Training Specialist (SME)
TextRLHF
As a Technical AI Training Specialist, I evaluated generative AI outputs for technical accuracy in IT, Finance, and STEM domains. I engineered multi-turn prompts to rigorously test LLM reasoning and safety alignment. My core tasks included Reinforcement Learning from Human Feedback (RLHF), translation of technical documents into model training data, and auditing model outputs for correctness.
• Consistently maintained a quality rating above 98% in RLHF workflows.
• Developed and architected complex prompts for robust model alignment.
• Engaged in red teaming to simulate adversarial conditions for AI safety validation.
• Contributed subject-matter expertise in technical, financial, and STEM domains.
As a Technical AI Training Specialist, I evaluated generative AI outputs for technical accuracy in IT, Finance, and STEM domains. I engineered multi-turn prompts to rigorously test LLM reasoning and safety alignment. My core tasks included Reinforcement Learning from Human Feedback (RLHF), translation of technical documents into model training data, and auditing model outputs for correctness. • Consistently maintained a quality rating above 98% in RLHF workflows. • Developed and architected complex prompts for robust model alignment. • Engaged in red teaming to simulate adversarial conditions for AI safety validation. • Contributed subject-matter expertise in technical, financial, and STEM domains.
2023 - Present