Data / AI QE Lead — Retail eCommerce

Data / AI QE Lead - Retail eCommerce Location-San Ramon, California or Beverly Hills, CA (5 Days Onsite) Job Type-Long Term Contract Role Summary The Data / AI QE Lead will define the quality engineering strategy for data pipelines, machine learning models, and AI-powered features across the retail eCommerce platform. This role bridges traditional data quality assurance and emerging AI/ML validation disciplines, ensuring that customer-facing capabilities - including product recommendations, personalization, search relevance, demand forecasting, and pricing intelligence - perform accurately, fairly, and reliably at scale. The role will build foundational QE practices for data and AI, partner with data engineering, data science, and product teams, and translate complex model behavior into measurable, business-aligned quality standards. Key Responsibilities Data Quality Engineering Define and own the QE strategy for data assets including customer, product, inventory, transaction, and behavioral event data Design and implement data validation frameworks covering completeness, accuracy, consistency, timeliness, and referential integrity Lead testing of ETL/ELT pipelines, data lake and warehouse layers (raw, curated, consumption), and real-time streaming pipelines Establish data contract testing practices between producing and consuming systems Build automated data quality monitors and alerting that operate continuously in production environments Partner with data governance and data stewardship teams to align QE standards with enterprise data policies AI / ML Model Quality & Validation Lead quality validation for ML models powering eCommerce capabilities: product recommendations, personalized search, dynamic pricing, demand forecasting, propensity models, and generative AI features Define model evaluation frameworks including offline metrics and online business metrics (CTR, conversion rate, AOV, revenue lift) Design and execute A/B and shadow testing strategies to validate model performance before and during production rollout Assess and test for model fairness, bias, and regulatory compliance across customer segments and product categories Validate model monitoring and drift detection systems to ensure production models remain within acceptable performance thresholds Define rollback and circuit-breaker criteria for AI features that degrade customer experience eCommerce Platform Integration Testing Drive end-to-end quality of data flows from customer interaction events through to AI feature delivery on site, app, and email channels Test integrations between the eCommerce platform and downstream data consumers including CDP, CRM, marketing automation, and analytics tools Validate real-time personalization pipelines for homepage, PDP, cart, and post-purchase experiences Ensure data quality for key eCommerce events: product views, add-to-cart, checkout, order confirmation, returns, and search queries Test search and browse relevance improvements driven by ML rankers and query understanding models Test Automation & Observability Build and scale automated data and AI testing frameworks integrated into CI/CD and model deployment pipelines Define and enforce data quality SLAs and embed automated gates into pipeline orchestration (Airflow, dbt, Spark, etc.) Implement observability tooling for data pipelines and AI model inputs/outputs in collaboration with data and ML engineering Drive adoption of synthetic data and data masking strategies to support safe, representative testing environments Establish version-controlled, repeatable test datasets for regression testing of ML models across release cycles Cross-Functional Partnership Collaborate with data scientists, data engineers, product managers, and business analysts to define acceptance criteria for data and AI deliverables Champion a culture of data quality ownership across data producers and consumers in the eCommerce organization Qualifications Required 7+ years in data or quality engineering, with at least 2 years leading a team or technical discipline Proven experience testing data pipelines (batch and streaming) across modern data stack technologies (Spark, Kafka, Airflow, dbt, Snowflake, BigQuery, Databricks, or similar) Hands-on experience with ML model evaluation techniques, including offline metrics and online experimentation (A/B testing) Strong SQL skills and proficiency in Python for data validation scripting and test automation Familiarity with eCommerce data domains: customer behavior, product catalog, order management, inventory, and digital marketing Excellent ability to communicate data and AI quality concepts to technical and non-technical stakeholders Preferred Familiarity with Generative AI applications (RAG pipelines, LLM-powered features) and emerging AI QE practices Knowledge of data privacy regulations (GDPR, CCPA) and their implications for test data management Experience in high-scale eCommerce environments (peak traffic events, flash sales, seasonal demand spikes)