I build and explore open-source AI and machine learning tools, with a focus on dependable agent systems, model evaluation, retrieval, and AI security.

• AI agents and reasoning: tool use, planning, memory, controlled workflows, and evaluation.
• Machine learning: data quality, reproducible experiments, calibration, drift, and useful baselines.
• LLMs and RAG: retrieval quality, grounded answers, citations, and provider-independent applications.
• AI safety and security: permission boundaries, adversarial testing, auditability, and human review.
• AI infrastructure and MLOps: deployable services, observability, model lifecycle, and cost measurement.

My research interests include artificial superintelligence (ASI) and the questions it raises about reasoning, alignment, evaluation, and safe autonomy. This is a research direction, not a claim that these projects implement superintelligence.

• sentinel observatory alan vo — Work in progress: sentinel-observatory-alan-vo
• ci failure triage alan vo — Import CI logs, fingerprint failure signatures, investigate same-commit mixed outcomes, and prioritize auditable remediation using measured job time and explicit investigation estimates.
• meeting minutes alan vo — Source-backed meeting minutes, independent approval and action tracking with optional grounded model suggestions
• identity risk workbench alan vo — Trace inherited identity grants, review risk evidence and simulate controlled remediation.
• code review ai alan vo — Multi-language static analysis and LLM-assisted code review engine with empirical defect detection benchmarking and Keycloak OIDC/SAML authentication.
• image dataset curator alan vo — Inspects uploaded images for perceptual duplicates, EXIF privacy issues, and dimension quality; curates stratified train/val/test splits using deterministic hashing; and exports ML-ready JSONL/CSV/COCO manifests.
• support intent observatory alan vo — Train and evaluate a local TF-IDF intent classifier from labeled customer support tickets, analyze confusion matrices, and triage uncertain tickets into human review queues.
• rag engine alan vo — Retrieval-Augmented Generation engine featuring hybrid dense-sparse retrieval, deterministic citation attribution, and faithfulness evaluation.

I use AI-assisted development. Useful evidence is in the implementation: working workflows, architecture decisions, reproducible tests, measured results, and explicit limitations. Repository READMEs should make these easy to inspect; repository count alone is not a measure of quality.

I am interested in AI/ML engineering, applied AI, and AI platform opportunities.

Alan Vo · alanvo@gmail.com · GitHub