I work part-time at Handshake AI as a Technical Engineer, training LLMs. So far, I have worked on safety optimization and software development efficiency.

• Developing and evaluating domain-specific prompts to assess large language model performance in software development and safety-critical contexts.
• Optimizing models to prevent the spread of dangerous information while maintaining accuracy and utility.
• Improving LLM efficiency in software development tasks through expert review and feedback.

I'm currently working on refining text-to-video and text-to-audio models.