_ _ __ __
| | | | __ _ _ __ _ _ _ __ | \/ | ___ _ __ ___ _ __
| | | |/ _` | '__| | | | '_ \| |\/| |/ _ \ '_ \ / _ \| '_ \
| |_| | (_| | | | |_| | | | | | | | __/ | | | (_) | | | |
\___/ \__,_|_| \__,_|_| |_|_| |_|\___|_| |_|\___/|_| |_|
AI Engineer - building things that think, learn, and ship to production.
Currently the founding AI engineer at Legix, where I built the entire AI stack from scratch GraphRAG pipelines, agentic workflows, multi-tenant learning systems, and end-to-end automation that actually runs in prod at 94.2% accuracy. That work helped us raise $1.6M pre-seed.
Before that, I was making autonomous vehicles navigate farms at Boson Motors and building meeting transcription bots that handle 10+ concurrent sessions at Auto BIM Route.
MS in Software Engineering from Arizona State. Published at IEEE. Certified on AWS, OCI, and IBM AI.
AI/ML · GraphRAG · RAG · Agentic Workflows · Context Engineering · Vector Search · LLM Eval · Confidence Calibration · GraphRAG · RLHF
languages · Python · TypeScript · JavaScript · SQL · C++
infra · AWS · GCP · Docker · Terraform · Temporal · Kafka
data · PostgreSQL · pgvector · Pinecone · Neo4j · Redis
web · Next.js · React · Flask · Hono
observability · Langfuse · Axiom · Sentry
- context ledger — a decision-tree architecture for AI systems that learn continuously
- agentic AI research — ran an 8-phase in-depth study on how agents behave with progressive tool access
- making GraphRAG actually work at scale across hundreds of classification categories