Data pipelines, warehouses, and observability. Agent workflows, model routing, evaluation, and usage analytics. Small, sharp tools with clean interfaces.
AboutI build data platforms, and the AI agents that run on top of them.
I'm Duyet — a Senior AI/Data Engineer. I left Fossil as the AI era was starting, and joined Cartrack to do data engineering for real: stabilize everything on a large ClickHouse warehouse, then build AI on top of that foundation.
Later I shipped more of the work fully through coding agents — a loop that runs in production and keeps improving itself. I still steer architecture and review; the agents do a lot of the typing.
On the side I try a lot of ideas. Some run well. Some die quickly. I keep building anyway, and I still ship updates almost every day.
Python, Rust, TypeScript · Spark, Airflow, ClickHouse, BigQuery, Kafka · Kubernetes, AWS, GCP, Cloudflare · LlamaIndex, AI SDK, LangGraph.
Agentic Engineering
Read the postMost of what ships here is written with coding agents. I describe intent, review diffs, and keep the architecture honest; they do the typing, the searching, and a lot of the grunt work.
- Claude
- ·Codex
- ·Grok Build
- ·Grok Bot
Languages
Python · Rust · TypeScript · SQL
Data
ClickHouse · Spark · Airflow · BigQuery · Kafka · dbt · DuckDB
Cloud & Infra
Kubernetes · AWS · GCP · Cloudflare · Terraform
AI & Agents
LangGraph · LlamaIndex · AI SDK · Claude API
Capabilities
Areas of expertise
8+ years of delivery across data, AI, and platform engineering — here's where the time actually went.
Data Engineering
8 yrEnd-to-end pipelines from raw event streams to analytics-ready tables. ClickHouse as the primary OLAP layer — petabyte-scale ingestion, columnar query optimization, and materialized view patterns. Airflow for orchestration; Spark for heavy batch transforms.
AI Agent Engineering
4 yrAgent frameworks, model routing, and evaluation infrastructure. AnyRouter for multi-provider fallback and BYOK routing. LangGraph and LlamaIndex for workflow orchestration. Usage analytics baked in from day one.
Cloud Infrastructure
6 yrKubernetes clusters on AWS and GCP, Helm chart authoring, Terraform for IaC. Cloudflare Workers for edge compute — zero cold-start, global, cheap.
Backend & APIs
7 yrREST and GraphQL services in Python, Rust, and TypeScript. Cloudflare D1 + KV for edge-native persistence. Durable Objects for stateful agent sessions.
Frontend & UI
5 yrReact and TanStack Start with SSG. shadcn/ui + Tailwind as the component layer across 8 sibling apps. Performance-first: sub-second LCP, no hydration overhead for static routes.
DevOps & Observability
5 yrGitHub Actions CI/CD with Turborepo caching. Structured logging into ClickHouse; MotherDuck for ad-hoc querying. OpenTelemetry traces for agent workflows.
Open Source
8 yrPublic libraries, dashboards, and reference implementations. rust-tieng-viet, ClickHouse Monitor, ShareHTML, LLM Timeline — built and maintained openly.