QA Engineer for AI Workflows on GCP & BigQuery

Momento Usa; Mexico; On-site; MXN 420,000 - 640,000; Full time

Job summary

Momento USA is seeking a hands-on QA Engineer to test Agentic AI workflows in a Google Cloud Platform environment. You will design, execute, and troubleshoot test scenarios, focusing on API testing, end-to-end validation, and AI-assisted test-case generation.

Responsibilities include testing AI-driven applications, validating data across datasets, and implementing human reviews for AI-generated tests to ensure robust coverage.

Qualifications

• Hands-on experience testing Agentic AI workflows or AI-driven apps.
• GCP experience including BigQuery, Cloud Run and Cloud Scheduler.
• Strong API testing and end-to-end testing skills.
• Experience with data validation across datasets.
• Practical use of AI tools for test-case generation and validation.

Responsibilities

• Test Agentic AI workflows and AI-driven applications in a GCP environment.
• Perform API testing and end-to-end testing to validate workflow functionality and data processing.
• Validate data accuracy and consistency across multiple datasets; investigate discrepancies and troubleshoot failures.
• Use AI tools to generate test cases and test plans, validate generated outputs, and ensure adequate test coverage.
• Implement human review and validation processes for AI-generated test cases.
• Identify defects, perform root cause analysis, and document test results.

Skills

Agentic AI testing

GCP experience

BigQuery

Cloud Run

Cloud Scheduler

API testing

End-to-end testing

Data validation

AI test-case generation

Independent test design

Tools

BigQuery

Cloud Run

Cloud Scheduler

AI testing tools

Job description

Momento USA is seeking a hands-on QA Engineer to test Agentic AI workflows in a Google Cloud Platform environment. You will design, execute, and troubleshoot test scenarios, focusing on API testing, end-to-end validation, and AI-assisted test-case generation.

Responsibilities include testing AI-driven applications, validating data across datasets, and implementing human reviews for AI-generated tests to ensure robust coverage.