LLM Trainer | AI Engineer | Pod Lead
TextFine Tuning
As LLM Trainer and AI Engineer at Turing, I led supervised fine-tuning (SFT) and RLHF cycles to improve factual accuracy and reduce hallucination rates in large language models. I developed scalable prompt libraries and automated benchmarking pipelines, collaborating closely with research and red teaming groups. My role entailed translating model metrics into actionable insights for technical and non-technical stakeholders.
• Oversaw SFT and RLHF evaluation cycles for factuality and ethical improvements.
• Built prompt libraries and benchmarking tools to enhance model adaptability.
• Participated in red teaming and ethical guardrail integration.
• Standardized performance and evaluation logs in JSON and plain text formats.
As LLM Trainer and AI Engineer at Turing, I led supervised fine-tuning (SFT) and RLHF cycles to improve factual accuracy and reduce hallucination rates in large language models. I developed scalable prompt libraries and automated benchmarking pipelines, collaborating closely with research and red teaming groups. My role entailed translating model metrics into actionable insights for technical and non-technical stakeholders. • Oversaw SFT and RLHF evaluation cycles for factuality and ethical improvements. • Built prompt libraries and benchmarking tools to enhance model adaptability. • Participated in red teaming and ethical guardrail integration. • Standardized performance and evaluation logs in JSON and plain text formats.
2025 - Present