LLM Trainer / Senior Python Developer (Full-Time Contract via Turing)
I fine-tuned a cutting-edge AI model for a major tech company using both SFT and RLHF to improve its ability to resolve complex Python coding challenges. My responsibilities included annotation, performance review, and calibration to align with strict client QA standards. I managed and coached a team of trainers to advance annotation accuracy and maintain project quality benchmarks. • Led data labeling and annotation tasks on computer code and reasoning chains for LLM training. • Provided calibration sessions, internal QA reviews, and resolved ambiguities with client stakeholders. • Awarded for outstanding contributions to model annotation and fine-tuning accuracy. • Developed onboarding and upskilling resources to standardize labeling workflow and ensure best practices.