Qa Analyst

Celebal Technologies; Mumbai City, Navi Mumbai; In loco; INR 600.000 - 900.000; Tempo pieno

Descrizione del lavoro

Celebal Technologies in Mumbai, India, is seeking a dedicated QA specialist to validate analytics models, dashboards, and AI/ML outputs. You will collaborate with domain experts to translate specs into test cases and ensure data accuracy across platforms.

You will design test datasets, recalculate metrics, and verify consistency of results across model versions, dashboards, and exports. A strong eye for edge cases and UI usability is essential.

Competenze

• 2–6 years of hands-on manual QA experience on data-heavy products such as dashboards, reporting tools, BI platforms, or AI/ML-driven apps.
• Strong spreadsheet skills in Excel or Google Sheets, including formulas, lookups, and pivot tables.
• Solid testing fundamentals: test case design, boundary and edge-case testing, regression testing, and defect lifecycle.
• Meticulous attention to detail and a habit of questioning results rather than taking them at face value.
• Experience with Azure DevOps or a similar tool for tracking bugs and managing test cases.
• Comfort in using Claude or similar AI platforms to simplify and speed work.
• Clear written and verbal communication, since you’ll translate between domain expert descriptions and engineers.
• Must work from our Navi Mumbai office.
• Basic SQL for pulling and checking data at the source.
• Experience testing AI/ML models and understanding accuracy, FP/FN, and model drift.
• Familiarity with finance domain and its metrics.
• Experience with SAP.
• Exposure to test automation, or interest in growing into it.

Mansioni

• Partner with our domain expert to translate specs into structured test cases with clear expected results and acceptance criteria.
• Build and maintain test datasets with known correct outputs, so every engine or model change can be checked against them.
• Independently recalculate key metrics in spreadsheets to verify the engine’s results, and dig into any discrepancies.
• Check AI model outputs against agreed acceptance criteria, compare results across model versions, and flag anything implausible or inconsistent.
• Probe edge cases such as missing or null values, zeros, outliers, rounding, and totals
• When a result looks wrong, help pin down whether the cause lies in the input data, calculation or model logic, or the way it’s displayed. UI testing
• Test dashboards, charts, tables, filters, drill-downs, and exports for functionality and usability.
• Review screens against designs and requirements to make sure the UI meets user expectations, and flag anything confusing or inconsistent
• Check that the same metric shows the same value everywhere it appears, whether on different screens, in tooltips, or in exported files.
• Verify behaviour across supported browsers and screen sizes Across both
• Write and maintain test plans and test cases.
• Log clear, reproducible bug reports (steps, expected versus actual results, screenshots, sample data) and follow them through to resolution.

Conoscenze

Manual QA

Data dashboards

Excel

Test case design

Edge-case testing

Azure DevOps

Claude AI

Clear communication

SQL basics

Finance domain

SAP

Test automation interest

Cross-functional collaboration

Strumenti

Azure DevOps

Claude AI

SAP

SQL

Descrizione del lavoro

Test and verify of the analytics models, application and UI against specs and data working closely with our domain expert and covering both functional and non functional aspects.

What youll do Analytics and AI model validation

• Partner with our domain expert to translate the specs and their domain knowledge into structured test cases with clear expected results and acceptance criteria.
• Build and maintain test datasets with known correct outputs, so every engine or model change can be checked against them.
• Independently recalculate key metrics in spreadsheets to verify the engine’s results, and dig into any discrepancies.
• Check AI model outputs against agreed acceptance criteria, compare results across model versions, and flag anything implausible or inconsistent, backed by clear examples.
• Probe edge cases such as missing or null values, zeros, outliers, rounding, and totals
• When a result looks wrong, help pin down whether the cause lies in the input data, the calculation or model logic, or the way it’s displayed. UI testing
• Test dashboards, charts, tables, filters, drill-downs, and exports for functionality and usability.
• Review screens against designs and requirements to make sure the UI meets user expectations, and flag anything confusing or inconsistent
• Check that the same metric shows the same value everywhere it appears, whether on diAerent screens, in tooltips, or in exported files.
• Verify behaviour across supported browsers and screen sizes Across both
• Write and maintain test plans and test cases.
• Log clear, reproducible bug reports (steps, expected versus actual results, screenshots, sample data) and follow them through to resolution.

What we’re looking for \

• 2–6 years of hands-on manual QA experience, ideally on data-heavy products such as dashboards, reporting tools, BI platforms, or AI/ML-driven applications.
• Strong spreadsheet skills in Excel or Google Sheets, including formulas, lookups, and pivot tables, plus real comfort working with numbers.
• Solid testing fundamentals, including test case design, boundary and edge-case testing, regression testing, and the defect lifecycle.
• Meticulous attention to detail and a habit of questioning results rather than taking them at face value.
• Experience with Azure Dev ops or a similar tool for tracking bugs and managing test cases.
• Comfort in using Claude or similar AI platforms to simplify and speed work
• Clear written and verbal communication, since you’ll often translate between how our domain expert describes a problem and what engineers need in order to fix it.
• Must work from our Navi Mumbai oAice. Nice to have
• Basic SQL for pulling and checking data at the source.
• Experience testing AI/ML models, along with a basic understanding of ideas like accuracy, false positives and negatives, and how model performance can drift over time.
• Familiarity with finance domain and its key metrics.
• Experience with using SAP
• Exposure to test automation, or an interest in growing into it.