At Turing, I work across 20+ AI projects in annotator and QA roles, evaluating and improving models spanning RLHF, SFT, RAG, CUA, and multimodal AI. My work includes comparing LLM outputs, testing multimodal capabilities, and curating structured training data.
I also design and evaluate computer-use agent tasks, from writing prompts to producing screen-capture proof of work. Across projects, I audit model outputs against detailed quality rubrics and have authored SOPs and training materials adopted team-wide.
Before Turing, I worked in financial analysis, finance management, and project consultancy. At TwinPeaks-MTCC Group, I managed reporting and budgeting for a PKR 975 Million project and used Excel and Power BI dashboards as part of work that led to an 8% decrease in overall project costs.
