Open to new work
A lab for
Backend & AI engineer building systems that hold up — RAG pipelines, LLM infra, and services that don't fall over at 3am.
Curious Head Labs · thinking through it
AI / LLM infrastructure
The engineering behind real AI products — RAG pipelines, model routing, eval frameworks, vector search — with the observability to catch silent failures before your users do. Shipped, not prototyped.
01
Distributed systems
Greenfield services or untangling a monolith that's outgrown itself. API design, service boundaries, persistence, observability — built to be handed off, not just to work.
02
Platform engineering
Cloud infrastructure engineers can reason about. Kafka, Kubernetes, Terraform, and alerting so on-call isn't a nightmare.
03
Staff engineering advisory
A thinking partner for engineering leaders. Architecture reviews, RFC feedback, technical strategy, and growing senior engineers — by the hour or on retainer. Useful when you need a second opinion without hiring a VP.
04
How I build AI
The real RAG pipeline behind Elio — from your inbox to a grounded answer. Retrieval, reranking, routed inference, and an eval loop watching for drift. Shipped, not sketched.
Gmail & notes
Your context
Ingest
OAuth2 · Spring
Chunk & embed
Pinecone
Retrieve & rerank
Hybrid search
Claude
Model routing
Streamed answer
Grounded, cited
Eval loop · traces · drift detection
0
Systems shipped
0
Years in backend
0
Uptime, always chasing
∞
Open questions