Selected work
Projects
A few representative builds. Filter by stack to narrow down.
- All
- A100
- Astro 5
- BigQuery
- Claude Sonnet 4.6
- Cloud Run
- Cloudflare Workers
- Docker
- DuckDB
- FBANK
- FastAPI
- GCP
- GitHub Actions
- GitHub Pages
- HPC
- Hugging Face
- Inspect AI
- Llama 3.1 8B
- Marimo
- NLP
- NumPy
- PDF processing
- PySpark
- PyTorch
- Pydantic
- Python
- Qwen2.5-7B
- React
- RoBERTa
- SQL
- Slurm
- Spark MLlib
- Streamlit
- Tailwind CSS v4
- Transformers
- TypeScript
- WebAssembly
- dbt
- mozjpeg
- mypy
- pdf-lib
- pdf.js
- pytest
- ruff
- scikit-learn
- synthetic control
2026
Synthetic evaluation lab for AI-agent reliability: 350 golden cases, 60 red-team cases, RAG evaluation, safe refusal, safety classifiers, prevalence estimation, human-review simulation, mitigation impact, release gate reporting, FastAPI, OTel tracing, and CI.
- Python
- FastAPI
- Streamlit
- Pydantic
- pytest
- ruff
- Docker
- GitHub Actions
- GitHub Pages
2026
Reproducible benchmark measuring how published adversarial prompts perform against 2026-era LLMs and whether prompt-only defences move the needle — with cross-judge validation and bootstrap confidence intervals.
- Python
- Claude Sonnet 4.6
- Llama 3.1 8B
- Inspect AI
- GitHub Actions
- pytest
- ruff
- mypy