An AI Engineer who
Because a demo that impresses is only half the job.
Currently, Software Engineer II, AI at Atlan.
I'm an AI / Software Engineer with 2+ years shipping production multi-agent systems — LangGraph orchestration, RAG, agentic harnesses, and evals — that solve real problems for real users.
At Atlan I've built support-automation, ticket-to-PR pipelines, metrics-glossary agents, and documentation agents that ran at tenant scale with measurable business impact: deflected tickets, saved hours, and shipped documentation for 700K+ data assets.
I like taking prototypes from "look, it demos" to "look, it's reliable" — the eval loops, the tool boundaries, and the boring plumbing that make agents actually usable in production.
Work Experience
Software Engineer II, AI · Feb 2024 – present
LangGraph · RAG · Glean · Zendesk
75 tickets/mo deflected · ~$60K–$100K projected savings
Support-automation agent on Zendesk with doc-grounded triage over Glean, specialist sub-agent routing, and human-escalation workflows. Lifted deflection from 18 → 75 tickets/month.
LangGraph · Claude Code · Linear · Cloudflare
First-pass correctness ~40% → ~75% on benchmark QA
Autonomous pipeline that reads a Linear ticket, spins up a Cloudflare sandbox via Harness, clones the repo, implements changes, and opens a review-ready GitHub PR.
Deep Agents · BI · SQL lineage
70% reduction in metric documentation effort
Auto-discovers KPIs from BI tools and SQL lineage, converts them into governed business metrics, and publishes a tenant-wide glossary with formulas and documentation.
Context Agents · Lineage · Usage
700K+ assets · 50 customers · 14 days · ~450× faster
Auto-generates plain-English documentation for tables and columns by learning from lineage and real usage patterns. 90%+ user acceptance; saved ~110K hours of manual writing.
that ships AI-native products end-to-end.
Selected Work
Full-stack AI
A full-stack AI Gmail client where a Python LangGraph agent drives the React UI via natural language — composing, navigating, filtering, and reading email.
Voice-first canvas
A voice-first thinking canvas that turns spoken decisions, plans, and problems into a live typed graph on tldraw.
Real-time voice agent
Real-time AI voice receptionist for clinics — callers talk naturally by phone or browser; the agent books appointments and sends confirmations.
AI agent for API validation
A LangGraph AI agent that validates API endpoint executability by fanning out Claude-powered ReAct agents per endpoint.
Self-correcting media agents
Two small, self-correcting media-generation agents built on Gemini + Google ADK — one for brand mockups, one for narrated explainer videos.
Science, explained
Turns any scientific paper or webpage into an immersive auto-playing documentary — with AI-generated visuals, narration, and live voice Q&A.
Doc intelligence
AI system for logistics document intelligence in TMS workflows — upload docs, ask grounded questions, run structured extraction with confidence and guardrails.
AI video meetings
AI-powered video meeting app for real-time voice conversations with custom AI agents — with live transcription and post-call summaries.
Menu → photography
Turns restaurant menus into stunning, professional food photographs using Gemini + Imagen 4.
Contact
Looking to join a cross-functional team building AI-native products end-to-end. Or have a project in mind? Drop a note.