Expert LLM Trainer & Evaluator
TelusTextPrompt Response Writing SFT
As an Expert LLM Trainer & Evaluator, I conducted RLHF and supervised fine-tuning to enhance the capabilities of advanced large language models. My work involved both the generation of high-quality synthetic datasets and detailed evaluations on reasoning and mathematical tasks. I optimized prompt strategies and ensured logical consistency, safety, and factual accuracy in model outputs.
• Led RLHF and SFT processes for frontier LLMs developing reasoning and coding skills
• Generated and curated complex mathematical and algorithmic datasets for supervised learning
• Evaluated LLM responses for accuracy, logical consistency, and safety in STEM domains
• Optimized prompts for advanced multi-turn reasoning in Python and mathematical proofs
As an Expert LLM Trainer & Evaluator, I conducted RLHF and supervised fine-tuning to enhance the capabilities of advanced large language models. My work involved both the generation of high-quality synthetic datasets and detailed evaluations on reasoning and mathematical tasks. I optimized prompt strategies and ensured logical consistency, safety, and factual accuracy in model outputs. • Led RLHF and SFT processes for frontier LLMs developing reasoning and coding skills • Generated and curated complex mathematical and algorithmic datasets for supervised learning • Evaluated LLM responses for accuracy, logical consistency, and safety in STEM domains • Optimized prompts for advanced multi-turn reasoning in Python and mathematical proofs
2024 - Present