Technical project management · Delivery systems · AI-enabled operations & integrations
I connect business priorities, delivery workflows, CRM, integrations, automation, and product environments into systems teams can actually run—so people know what moves next and leaders can trust what they see.
Technical Project Manager · Delivery Systems Architect · AI-Enabled Operations and Integrations Lead
15+ years across software delivery, operations transformation, consulting, and global remote teams · Barranquilla, Colombia
The model moves from a business outcome to clear ownership, controlled execution, verified evidence, and one explicit next decision.
I define the operating model, source-of-truth boundaries, workflows, acceptance criteria, integrations, reporting, and release controls that connect business decisions to execution.
I work across leadership, product, engineering, QA, operations, and client teams—and use AI-assisted development to move from requirements into working interfaces, automations, integrations, and products.
First clarify the process, ownership, handoffs, and evidence. Then automate what should repeat.
Metrics belong to specific engagements and are shown with context in the related case studies.
Caul Group / Sympli Mortgage
The verified loan-operations integration is a live production system.
The related agent experience remains gated by policy, authentication, roster, and backend decisions.
Public evidence excludes borrower data, credentials, internal URLs, and proprietary operating records.
Connected loan operations, execution visibility, and engagement workflows without duplicating the system that governs the loan.
Read the case study ↗Select a system to see what it owns, what is allowed to move, and what evidence is required before the next action.
Selected system
03 / Operating layer
Makes milestones, tasks, exceptions, and next actions visible to the team.
01Canonical truth stayed where the business already governed it.
02Borrower-facing uncertainty failed safely and escalated internally.
03Duplicate-risk controls were built into synchronization, while automation execution cost fell by approximately 55%.
Each system begins with the operating truth: who owns what, how work moves, what can fail, and what evidence earns the next decision.
TH3RD GROUP
Built the public website and operating systems that connect strategy, revenue, delivery, market readiness, and execution.
The commercial, operational, integration, and intelligence layers work together without creating competing sources of truth.
View case study ↗FastVideo
Structured a six-stage AI video workflow and the operating layer required to review, render, launch, and improve it.
Script → Voice → Visual → Music → Output → Export
View case study ↗Jane’s Weather / ACM
Made complex product, API, UAT, and release work visible, testable, and easier to coordinate across cross-functional teams.
75% shorter PR review cycle · 35% greater QA visibility
View case study ↗Jira
Turned Jira from a passive tracker into a workflow that required the right evidence before work moved toward release.
Project-management workflow designed around the real delivery lifecycle.
View case study ↗Victus Global
Connected business-development intake, approvals, project creation, delivery, and customer-success handoff in one governed operating model.
Business logic, ownership, and handoffs defined before automation.
View case study ↗Tools can accelerate implementation. They cannot decide which truth matters, where the risk sits, or what proof makes the result safe to use.
Turn business ambiguity into a clear objective, measurable success, and explicit trade-offs.
Weather delivery: broad platform expectations became testable requirements and release criteria.Define sources of truth, boundaries, workflows, data movement, ownership, and exception paths.
Mortgage operations: ARIVE remained authoritative while n8n coordinated approved movement across the operating flow.Create the tasks, interfaces, automations, controls, documentation, and operating rhythm required to deliver.
TH3RD GROUP: commercial, operational, integration, and intelligence layers were designed to work together without competing for truth.Use QA, UAT, reconciliation, evidence, and feedback to decide what ships, what holds, and what changes next.
FastVideo: review, render, and launch controls were tied to the reliability of the final output.I use AI-assisted development to move from architecture into working software, integrations, automations, and operating interfaces. I remain responsible for the business outcome, workflow logic, system boundaries, acceptance criteria, validation, security decisions, and final acceptance. Specialist engineering or security review enters wherever the risk or technical depth requires it.
The through-line is not a job title. It is making complex work legible, governable, and ready to move.
Controls, service, ownership, and measurable cycle improvement.
CRM, ERP-lite systems, automation, and role-based visibility.
Requirements, APIs, QA, UAT, release readiness, and global teams.
Architecture-led implementation with validation and guardrails.
Start here
If the team is working hard but still chasing updates, duplicating data, or relying on one person to hold the workflow together, the operating layer is already the bottleneck. I help define the truth, connect the work, and build the controls that let execution move without guessing.
