Two-time founding engineer. Building AI that remembers.
· · ·
AI Engineer. Building things that think, learn, and ship to production.
Currently the Founding Engineer at Cognisos, working on the architecture for intelligent systems: AI that remembers, reasons, and evolves at runtime. Most of the day-to-day is the founding-engineer mix I love. Setting the technical foundation, owning architecture across the stack, and shipping research into production.
Before this I was 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 running in prod at 94.2% accuracy. That work helped us raise $1.6M pre-seed.
Earlier 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 · Agentic Workflows · Context Engineering · Vector Search · LLM Eval · Confidence Calibration · MCP |
| languages | Python · TypeScript · JavaScript · Rust · 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 |
· · ·
| 01 | agent memory | long-horizon state, how agents remember and recover across sessions |
| 02 | agentic AI | 8-phase study on how agents behave with progressive tool access |
| 03 | graphrag | scaling to hundreds of classification categories |
· · ·
| portfolio | x · @Itious_ |
