Quality Analyst Reporting

Key Responsibilities

1. Intelligent Risk-Based Auditing

• Targeted Sampling: Shift away from traditional random 10% sampling to design and execute a risk-based sampling model driven by historical error metrics.
• Efficiency Optimization: Focus expert auditing resources exclusively on high-probability error transactions (e.g., complex multi-item checkouts, tenured anomalies, or edge cases flagged by AI).

2. In-Line Guardrails & Feedback Loops

• Partner with the Technical Project Co-ordinator and Systems Engineering teams to design real-time feedback loops and automated validation gates directly within core auditing tools (GRIME and ASGARD).
• Stop data discrepancies at the entry point, ensuring errors are flagged and corrected before they exit the primary audit phase.

3. Data Quality & Root Cause Analysis (RCA)

• Systemic Issue Diagnostic: Conduct deep-dive Root Cause Analysis (RCA) on recurring database discrepancies to isolate underlying drivers (e.g., software tool lag, vague annotation guidelines, or ML model classification gaps).
• Guideline Optimization: Translate RCA findings into immediate corrective actions, updated documentation playbooks, and training huddles for the reporting floor.

4. AI Model Guardrails & Collaboration

• Model Validation: Act as the authoritative validation layer for AI-driven engines, auditing and labeling the automated classification outputs to ensure a near-100% database gold standard.
• Mitigate Model Drift: Identify patterns where AI models begin to show bias or drift due to new cashier behaviors or store layouts, feeding structured corrections directly back to the Research and ML development teams.

Candidate Profile & Requirements

• Experience: 3+ years of experience in Quality Assurance, Quality Engineering, or Data Quality Control within high-volume data processing, analytics, or tech operations environments.
• Analytical Toolset: Strong proficiency in data analysis, including statistical tracking, root cause analysis (RCA), and basic data tools (Excel, SQL, or dashboard reporting tools like BI).
• AI/ML Familiarity: Experience working alongside automated systems, data annotation platforms, or ML pre-labeling loops is highly preferred.
• Problem-Solving Mindset: A proactive, "build-the-guardrail" attitude—someone who seeks to fix the process rather than just report the error.
• Communication: Exceptional collaborative skills, with the ability to bridge communication between front-line annotators, technical project coordinators, and ML engineers. 
• Education: Graduation in Engineering background