skills

Core Research Skills

• LLM evaluation protocol design and benchmark methodology.
• Belief-structure analysis for multi-actor social reasoning tasks.
• Annotation pipeline design, quality review, and consensus-driven validation.
• Error analysis across schema-level and structure-level model behavior.

Machine Learning and AI

• Computer Vision, NLP, multimodal reasoning workflows.
• PyTorch, TensorFlow, Scikit-Learn, applied model experimentation.
• Model comparison across open-source and API-based LLM families.
• Metric-driven evaluation (classification metrics, similarity metrics, structured audits).

Software and Systems

• Python, C/C++, Java, JavaScript, SQL, PHP.
• Full-stack development with Astro, Go, PostgreSQL, MERN, and LAMP.
• Dockerized workflows and deployment on DigitalOcean.
• API integration and automation with cloud tooling.

Collaboration and Delivery

• Agile project leadership, sprint planning, and team coordination.
• Research presentation, technical writing, and cross-functional communication.
• Mentorship and instruction experience supporting large student cohorts.