WORK
Selected work
Seven systems with architecture and LLD, including an ops dashboard, Go telemetry ingestion, a Node.js API platform, and a prototype-to-production deploy. Client names are withheld; the designs are not.
01
AI product development
PII · generation
Synthetic data platform
A production pipeline that scans documents and schemas once, writes a masking blueprint, then fans out synthetic copies with human review, vaultless tokenization, and an agent tool bus.
Detect once, generate many
Ingest · retrieve
Knowledge assistant
Three deployables: a document ingest pipeline into vector search, an orchestrator API, and a chat client. Answers are generated from indexed chunks, not from a naked prompt.
Cite-or-refuse retrieval
LangGraph · trace
SRS generator
Retrieve tickets, wiki pages, and indexed docs, then generate a structured software requirements spec. Features become tickets, gaps close the loop, traceability stays read-only.
Six-layer generate → trace loop
02
Backend & API engineering
Go · ingest
Telemetry ingestion
Python ingestion needed more instances than the throughput justified. GC pauses under load dropped client connections, retries added load, and the fleet was sized for that loop. The ingest tier is now a Go worker pool.
Shed load before it queues
Node · jobs
API platform
The product API did HTTP, long jobs, and inbound webhooks in one request cycle. Reports timed out, a failed webhook was gone, and one shared key could touch every resource. The request path is now Fastify. Slow work is a BullMQ job the client polls.
The request is not the job
03
Cloud & DevOps
04