I design and build the AI-driven automation, enrichment, CRM, and analytics infrastructure behind modern go-to-market teams — turning manual sales & marketing motions into production systems that operate unattended, at scale, with duplicate-safety and deliverability built in.
I sit at the intersection of engineering and revenue — designing the pipelines that connect data providers, CRMs, outreach tools, and analytics, then writing the automation that runs them without hand-holding. AI is native to how I build: enrichment agents, reply classifiers, and content pipelines are core tools, not add-ons, so the unglamorous parts — deduplication, deliverability, data integrity — stay as solid as the flashy ones.
Salesforce-certified. Lifecycle automation, lead routing, cross-object sync.
Multi-mailbox sequencing, self-healing, compliance-aware enrollment.
Enrichment agents, reply classifiers, content pipelines with memory.
ICP sourcing, verified-email gating, SOQL / SQL reporting.
Mailbox validation, SPF/DKIM/DMARC, bot-vs-human integrity.
Live GTM dashboards on the edge, webhook orchestration.
Enrich a raw company, enroll it into multi-mailbox outreach, classify every reply, and route qualified leads into the CRM — no manual handoffs.
Finds a prospect's employer and a verified email from just a name, combining an LLM research agent with deterministic pattern-guessing. Won a head-to-head bake-off against a commercial enrichment platform.
Reads every inbound reply, separates real humans from auto-replies and bounces, and routes humans to sales in real time. Fixed a truncation bug that was silently dropping genuine replies.
Button-triggered email broadcasts with fingerprint dedup so nothing sends twice, plus forensic bot-filtering that stripped most scanner noise from engagement metrics.
Led the migration of the org's single source of truth between CRMs inside a shared enterprise Salesforce org — a config-driven “Lead Brain / Account Brain” architecture where adding a product is one config entry.
Covers the full trial lifecycle — signup through demo booking to show/no-show tracking — config-driven per account, so sales adjusts cadence without touching code.
Most of a pipeline should stay deterministic. These are the points where the right answer depends on reading something — and a rule would get it subtly wrong.
Reads every inbound reply, separates real humans from bounces and auto-replies, routes humans to sales in real time.
Researches a prospect's employer and finds a verified email from just a name — an LLM research agent plus pattern-guessing.
Listens to demo-call transcripts and extends a trial automatically when a prospect explicitly asks — sales keeps full override.
Closed loop from market-intelligence scanning to AI writers to performance analysis, with memory across cycles.
Every project above is one piece of this. Multi-market sourcing, an agentic n8n layer, a rebuilt multi-tenant Salesforce org, and a live dashboard — one engineer, every layer.
Open to Go-to-Market Engineering and Revenue Operations roles. If you're building revenue systems that should run on their own, let's talk.