C

Carlos Garcia

About

Detail

Monterrey, Nuevo Leon, Mexico
Contact Carlos regarding: 
work
Full-time jobs
Starting at USD5k/month
Flexible work
Starting at USD35/hour
groups
Networking

Timeline

work
Job
school
Education
folder
Project

Résumé

Jobs verified_user 0% verified
  • Instructure
    Senior QA Engineer
    Instructure
    Sep 2024 - Current (1 year 11 months)
    Web platform QA for Parchment, Instructure's digital credentials and academic records division. • Built an AI-assisted testing pipeline using Claude Code that reduced test design time from ~4 hours to under 40 minutes per test plan, consistently, across all stories • Deploy Claude agents to automate test case generation, coverage analysis, and bug report drafting within active sprint workflows • Trained and iterated bug detection workflows using Claude, integrating AI output directly into sprint delivery • Design and execute end-to-end test plans covering credential workflows, user roles, and data integrity. Requirements first, never implementation-first • REST API testing via Postman across authentication flows, data contracts, and error h
  • H
    Founder & Ai Qa Practitioner
    Holteck
    Jan 2024 - Current (2 years 7 months)
    Independent AI QA research practice focused on testing, evaluating, and validating AI systems in production. • Built qa-ai-workflow: a Claude API + Playwright pipeline that converts user stories into test plans, Playwright specs, and executable bug reports automatically, end to end, no manual handoff • Al-Human Interaction Observatory: documented and replicated 9 behavioral patterns in LLM-assisted workflows, including confident incomplete delivery, where models present partial outputs with full-confidence framing, eroding user trust in ways that don't surface in standard eval rubrics. Public methodology and field notes. • Built ai-eval-toolkit: reproducible LLM evaluation experiments with fixed stimuli, versioned protocols, automated runne
  • Independent
    Senior Qa Consultant
    Independent
    Jun 2021 - Aug 2024 (3 years 3 months)
    Embedded senior QA resource across multiple US-based product teams. • Built test strategies from business requirements and functional specs; coverage always grounded in user intent, not what the developer happened to implement • Led large-scale regression cycles across web and mobile platforms ahead of major releases • REST API validation via Postman; SQL-based backend validation and defect investigation • Integrated AI tooling to accelerate test case generation and surface coverage gaps across multiple concurrent engagements • Azure DevOps for end-to-end test management and traceability
  • C
    Software Test Lead
    Congruent Technologies Inc.
    Mar 2014 - Jun 2021 (7 years 4 months)
    • Defined test coverage from business requirements and risk assessment, not implementation scope • Mentored junior QA engineers and established team-wide testing standards and methodology • Coordinated with business analysts to align acceptance criteria with test case design • Led large-scale regression cycles across web and mobile platforms
  • accenture
    Senior Software Test Lead
    accenture
    Jan 2010 - Jan 2014 (4 years 1 month)
    Led QA team of 25, Agile delivery, functional and regression testing across enterprise projects
  • EMC
    Test Lab Manager
    EMC
    Jan 2008 - Jan 2010 (2 years 1 month)
    Managed nearshore QA team of 23, hardware and software validation, virtual machine testing environments
  • SOFTTEK
    Software Test Execution
    SOFTTEK
    Jan 2006 - Jan 2008 (2 years 1 month)
    Manual and automated testing, Layered Drivers validation, Perl automation scripting
Education verified_user 0% verified
  • Centro de Estudios Universitarios Monterrey
    Bachelor's Degree, Computer Software Engineering
    Centro de Estudios Universitarios Monterrey
    Aug 2000 - Current (26 years)
Projects (professional or personal) verified_user 0% verified
  • H
    QA-AI-workflow
    Holteck
    Mar 2026 - Current (5 months)
    Claude API + Playwright pipeline: user story in → test plan → Playwright specs → executed results → bug reports out. TypeScript + Node.js. Includes --mock mode for zero-API-cost demo runs. Built to demonstrate requirements-first AI-assisted QA at scale.
  • H
    AI-eval-toolkit
    Holteck
    Mar 2026 - Current (5 months)
    Reproducible LLM evaluation experiments with fixed stimuli, versioned protocols, automated runners, and CSV result logs. Experiment 001 complete: Skill Activation Reliability under conversational noise, 10 controlled runs, results published.
  • H
    AI-Human Interaction Observatory
    Holteck
    Mar 2026 - Current (5 months)
    Field research on AI-human behavioral patterns. 9 structured observations from real working sessions, each with context, observed behavior, hypotheses, and replication design. 20 years of QA methodology applied to AI systems that have no specification.