AppliedAIEngineer.Buildingatthefrontierof AI.
I design and ship LLM-powered systems, document intelligence pipelines, and real-time AI workflows — turning ambiguous, high-friction problems into production software that scales.ships.compounds.just works.
Currently Software Engineer at Randomwalk AI, where I design LLM-powered backends for document intelligence and automation — shipping systems that process high-volume documents at scale, orchestrate async job pipelines, and power internal nudging workflows.
My work sits at the intersection of LLMs, backend engineering, and pragmatic system design. I care about latency, reliability, and cost — and about making AI feel like infrastructure you can trust.
Previously at docu3C building React frontends. Hackathon winner. NVIDIA Deep Learning Institute alum.
A short trail of building.
Designing and deploying LLM-powered document processing systems for regulated, high-volume document workflows at scale. Built async bulk-job pipelines, AI-driven nudging systems, and optimized workflows for cost, latency, and reliability with retries, fallbacks, and guardrails.
Built backend microservices and REST APIs powering early AI applications. Automated internal workflows and shipped production features in tight agile cycles — the runway into a full-time role.
Developed responsive React interfaces and collaborated with design to raise usability and accessibility — where the obsession with polish and pixel-perfect detail started.
Things I've built.
A small set of recent work — production systems, weekend experiments, and the edges between them.
TeamPulse AI
Workspace Dashboard
Built in about an hour — AI workspace that turns Google Workspace signals (emails, calendar, tasks) into structured intelligence. Gemini extracts blockers, decisions, and workload summaries automatically, delivering a live view of team health.
Synchronized
Streaming Platform
Multi-user streaming system with frame-accurate synchronized playback — built for real-time state, low-latency WebSocket messaging, and audiences watching together across devices.
StreamSense AI
Monitoring
A live pipeline ingesting CCTV RTSP streams and running activity detection on the edge — with alerting and periodic AI-generated summaries so humans only look when it matters.
AI Document
Intelligence System
End-to-end platform for document classification, extraction, and validation using LLMs with a synthesizing engine. Backend architected for bulk processing with async job orchestration — turning hours of manual review into minutes.
Shipped on weekends.
Personal tools, half-jokes, and things I built because I wanted them to exist. Click any row for the long-form story — what it does, what's under the hood, and where to try it.