Forward-Deployed / Solutions Engineer

I ship AI systems into live customer production — and own them through renewal.

I work where AI systems, customer-facing engineering, and production reality meet. I scope the real problem, build the system, deploy it onto live customer infrastructure, and stay on through the failures a demo never shows you — carrier verification, number porting, voice quality, off-script edge cases. The interesting work starts after “it works on my machine.”

Résumé GitHub Email Book 15 min

CS @ University of Florida (B.S. / M.S.) Orlando, FL AI voice · telephony · data pipelines

Production Case Study

Designing, deploying, and owning a production AI voice system.

Daniel Monzon Automation (DMA) — a bilingual (English / Caribbean-Spanish) AI voice receptionist deployed onto live small-business phone lines, with structured lead capture wired into CRM and notifications. I own this system end-to-end — discovery through renewal.

Architecture

Conversation Retell

Orchestrates the voice agent — call routing, turn-taking, and tool/webhook calls.
Voice synthesis ElevenLabs TTS

A dedicated Caribbean-Spanish voice for native-sounding bilingual handling.
Telephony Carrier · Google Voice · Twilio

Carrier numbers, call-forwarding bridges, number porting, and Twilio for SMS.
Orchestration + data Zapier → Postgres → HubSpot

Post-call webhooks feed a Zapier extraction pipeline (8 structured fields) into Postgres as source of truth, then push to HubSpot CRM and fire email/SMS lead alerts.
Web concierge Chatbase — "Mona"

A site assistant with its own lead-alert path.
Infra Hetzner VPS · Postgres

Self-hosted VPS with Postgres as the durable store.

How data moves

01 Caller dials in
02 Retell answers in the selected language
03 Conversation completes
04 Webhook fires
05 Zapier extracts 8 structured fields
06 Writes to Postgres + pushes to CRM
07 Lead email / SMS fires
08 Owner gets an actionable lead within seconds of hangup

Key technical decisions / tradeoffs

Postgres is the source of truth rather than trusting CRM state, so lead data survives integration hiccups.
Call forwarding runs as a live bridge during number porting to guarantee zero dropped calls.
Delivery channels are separated — voice/email ship independently of SMS — so a single carrier gate can’t block the whole system.

Production problems I diagnosed and fixed

Zero-downtime number porting

Symptom: A client’s existing business number had to move onto the new system, but Google Voice porting takes days and the business cannot miss a single call.
Diagnosis: Treat the cutover as a live-traffic migration, not a config change.
Fix: Stood up call forwarding as a bridge so the AI agent answered immediately while the port completed in the background.
Outcome: Clean cutover — no missed calls, no customer-visible downtime.

LessonA cutover is a live-traffic migration, not a config change. Bridge the traffic first, move the plumbing second, and you never drop a call.

Toll-free / SMS carrier verification

Symptom: SMS lead notifications weren’t delivering.
Diagnosis: Not a code bug — messaging was gated behind toll-free verification with the carrier (Twilio). A compliance/carrier state, not application logic.
Fix: Decoupled the pipeline so voice + email lead delivery shipped immediately, with SMS wired in the moment verification cleared.
Outcome: Lead capture went live without waiting on the carrier; SMS layered in cleanly after.

LessonIn telephony, a large share of “bugs” are carrier / compliance states — the fix is diagnosis and sequencing, not more code.

Bilingual voice quality (dialect-level QA)

Symptom: Generic Spanish TTS sounded flat and non-native for a Caribbean-Spanish-speaking customer base.
Diagnosis: “Speaks Spanish” is not the bar; dialect and pronunciation are the bar.
Fix: Built and tuned a dedicated Caribbean-Spanish voice so Spanish calls sound native rather than translated.
Outcome: Bilingual calls that hold up with real customers — measuring output quality, not just capability.

LessonCapability isn’t quality. “It speaks Spanish” clears a demo; dialect and pronunciation are what hold up on a real call.

Reliable structured extraction on off-script calls

Symptom: Real callers go off-script — partial info, wrong language selected, early hangups — which threatened the structured lead output.
Diagnosis: The post-call extraction needed to degrade gracefully instead of failing.
Fix: Built fallback handling so every call still yields an actionable lead across all 8 fields where possible.
Outcome: The owner always receives something usable, regardless of how the call went.

LessonReal callers never match the happy path. Design the pipeline to degrade gracefully so every call still yields something the owner can act on.

Writing

Engineering writeups.

Writeups on systems I’ve built and problems I’ve debugged.

Sandbox Isolation Design

Architecture and security tradeoffs for safely running untrusted / experimental code, and how isolation choices interact with scaling.

systems
security
infra

Read →

Inside a Production AI Voice Architecture

Full teardown of the DMA stack: Retell + ElevenLabs orchestration, the Zapier → Postgres → CRM data path, and the telephony/carrier lessons that only show up in production.

AI voice
systems
production

Read →

Deciding When a System Is Allowed to Ship

A pre-registration discipline for gating systems into production: pre-commit the bar, earn each rollout stage from backtest to paper to live, and fail safe by default. Drawn from quant research, applied to anything that ships.

reliability
methodology
risk

Read →

Selected Work

Selected projects.

Prioritized for engineering depth over business outcomes.

quantlab

Quantitative trading research system with pre-registered risk limits — daily/weekly HALT and drawdown KILL gates — and a backtest → paper-trade → live gating pipeline.

Why it’s interestingDisciplined, reproducible experimentation infrastructure with hard risk controls: strategies across equities and crypto on separated broker (Alpaca) accounts. Systems + rigor.

Python
quant
risk
Alpaca

github.com/danielfmonzon/quantlab ↗

PipelinePulse

An agentic pipeline that pulls open Salesforce opportunities via REST, scores deal health with deterministic rules, and posts an LLM-written daily pipeline digest — with recommended next actions — into Notion.

Why it’s interestingRules do the math, the LLM does the language — a deliberate split for reliability. Config-driven, Dockerized, and scheduled via GitHub Actions.

Python
Claude
Salesforce
agents
LLM
tool-use

github.com/danielfmonzon/pipelinepulse ↗

HelloG8r — Secure Code-Execution Platform

A Docker-hardened service that runs untrusted student Python safely — network-isolated, read-only filesystem, dropped Linux capabilities, no-new-privileges, and enforced CPU/memory limits.

Why it’s interestingOS-level isolation done properly, behind a validated REST execution API — spanning a Go backend, a Clojure problem generator, and a Next.js/TypeScript frontend.

Go
Docker
security
infra

github.com/TheShmill/hellog8r ↗

Webots RL Teaching Tool

A reinforcement-learning robotics simulation (cbt_00024) built for a university AI course: parametric training missions, reward shaping, and reproducible training runs.

Why it’s interestingApplied RL + simulation + pedagogy, shipped against real stakeholder acceptance criteria.

RL
Webots
simulation
robotics

How I Work

I like working where software meets customers.

I’m at my best translating a messy customer problem into a technical solution, owning the deployment, and debugging the unclear failures that live between systems and the real world. I move comfortably between the terminal and the stakeholder call — explaining a carrier-verification delay to a non-technical owner in the morning and shipping the fix that afternoon.

University of Florida CS (B.S. / M.S.), prior analytics at Synchrony Financial, and AI research in an NVIDIA-partnered lab.

Let’s talk

Building something where AI systems meet real customers?

Résumé GitHub Email Book 15 min