LLM Trainer (AI Training) | Turing
RLHFAs an LLM Trainer at Turing, I facilitated RLHF workflows for Large Language Models focused on code generation and prompt engineering. My work involved designing adversarial and edge-case prompts, evaluating code outputs for accuracy, and providing granular response feedback. This experience also included dataset curation, detailed annotation, and AI quality evaluation across various programming languages. • Designed and executed code evaluation protocols for LLM outputs. • Provided response rankings and ideal coding solutions for model improvement. • Performed prompt engineering and dataset annotation for instruction following and logical reasoning. • Focused on model alignment, reliability, and quality enhancement in code generation systems.