LLM Post-Training Intern
Text
Supported post-training of large language models by performing prompt engineering and evaluating model responses. Annotated structured and unstructured text data to assess correctness, relevance, and consistency of AI outputs. Conducted manual review for hallucinations, bias, and formatting issues, ensuring adherence to guidelines. •Refined prompts to enhance LLM response quality.
•Validated annotations with basic Python scripts and rule-based checks.
•Identified problematic model outputs and flagged them appropriately.
•Followed feedback loops to improve annotation quality and model reliability.
Supported post-training of large language models by performing prompt engineering and evaluating model responses. Annotated structured and unstructured text data to assess correctness, relevance, and consistency of AI outputs. Conducted manual review for hallucinations, bias, and formatting issues, ensuring adherence to guidelines. •Refined prompts to enhance LLM response quality. •Validated annotations with basic Python scripts and rule-based checks. •Identified problematic model outputs and flagged them appropriately. •Followed feedback loops to improve annotation quality and model reliability.
2026 - 2026