Writing

Notes on AI engineering.

Long-form thinking on architecture, applied AI and building enterprise platforms. These are early drafts — full articles are on the way.

How I Built an Enterprise AI Recruiting Platform

The architecture behind TalentPike — multi-tenant SaaS, semantic matching, explainable ranking and a local LLM keeping candidate data in-house.

Why keyword filters miss great candidates, how vector embeddings fix it, and where a hybrid approach beats both.

When data residency rules out hosted models, local LLMs via Ollama can power real enterprise AI — here's the pattern.

Tenant isolation, RBAC, secrets and zero-downtime delivery — the foundations every enterprise SaaS needs from day one.

Turning behavioral telematics into proactive coaching with clustering and classification — the approach behind a 95%-accuracy risk model.

Fusing prices, macro data, news and EDGAR fundamentals into an ensemble pipeline — with backtesting discipline at the center.

The full journey a resume takes — parsing, confidence scoring, embedding, hybrid ranking — and why the 'why' matters as much as the score.