Research Experience

Independent Researcher

AI Safety Research Collaboration Remote | December 2025 - Present

  • Engineered an evaluation harness using OpenAI and Anthropic APIs to simulate reinforcement learning training.
  • Evaluated frontier models (GPT 5.2, Claude Opus 4.5, etc.) on their propensity to resist RL training under misaligned goals, identifying a novel failure mode in AI models.

Research Fellow

Supervised Program for Alignment Research (SPAR) Remote | September 2025 - Present

  • Developed evaluation pipelines to quantify goal drift in language model agents on long-horizon tasks.
  • Designed experiments to study how conditioning stronger models on weaker models’ context affects goal drift.
  • Led the writing and submission of the first-author paper to ICLR Workshop 2026.

Research Assistant

Trustworthy ML Lab La Jolla, California | June 2025 - August 2025

  • Investigated chain-of-thought (CoT) reasoning and faithfulness in large language models.
  • Developed and tested steering-vector methods for improving CoT faithfulness, achieving promising preliminary results on the “hint” setup from Chen et al. (2025).

Industry Experience

Associate Data Scientist, Refinance Team

Jerry Services Inc. Chicago, Illinois | December 2023 - July 2024

  • Led the analysis of A/B tests and development of ML models for the refinancing product which reduced credit pull costs by 70% with no negative impact on loan volume.