AI safety research, infrastructure, and BioML. Currently a research intern at EleutherAI (SOAR), working on cheap evaluation methods for inoculation prompting. In terms of engineering I build data pipelines, backend services, and ML systems for AI safety and BioML research.

San Diego, CA · LinkedIn · Email

Inoculation prompt evaluation — EleutherAI SOAR. A low-cost heuristic for predicting when a training-time inoculation prompt suppresses a target trait without expensive finetuning runs. Some skills/tools: Fine-tuning infrastructure, LLM-as-judge evaluation pipeline, Tinker API and cloud GPUs.

UmamiBench — a benchmark measuring scientific judgment in frontier models. Some skills/tools: Construct definition, task rubric design, and the model evaluation pipeline.

HELIX — ML architectures for identifying selective RecA antibiotic adjuvants that reduce quinolone resistance. Designed the full computational stack: a docking pipeline over millions of compounds (20 → 2,500 ligands/hr via sharding, caching, and parallelization; 40k+ CPU hours on GCP), custom potency classifiers, and dataset curation.

Some current safety work isn't public yet.

Selected merged pull requests from @OpenCodingSociety:

Mechanistic interpretability and evaluation · Empirical Alignment and Pretraining · ML for biology and scientific imaging · Data pipelines and backend infrastructure