Key Responsibilities
Analytics Strategy & Business Discovery
Partner with business stakeholders and executive leaders to understand decision-making processes and critical business questions.
Identify opportunities where AI can improve insight generation, decision support, and overall business outcomes.
Translate complex business requirements into scalable analytics capabilities and AI-powered solutions.
Define KPIs, metrics, and success measures that support digital commerce initiatives.
AI-Powered Analytics Experiences
Design and develop agentic AI assistants that enable users to interact with business data through natural language.
Architect Retrieval-Augmented Generation (RAG) workflows that connect AI systems to structured and unstructured data sources.
Build semantic models that help AI systems understand business concepts, customer behaviors, products, metrics, and operational terminology.
Continuously improve answer quality, explainability, grounding, trustworthiness, and user experience.
eCommerce Decision Intelligence
Develop solutions supporting:
Customer Journey Optimization
Personalization
Product Recommendations
Audience Segmentation & Targeting
Experimentation & A/B Testing
Real-Time Decisioning
Create executive reporting and decision-support experiences.
Translate data-driven insights into actionable business recommendations.
AI Evaluation & Quality
Define evaluation frameworks for analytics-focused AI applications.
Assess solution quality, including accuracy, relevance, grounding, usability, and business impact.
Monitor adoption, performance, cost efficiency, and operational health of AI systems.
Establish processes for continuous improvement and quality assurance.
Platform Delivery & Collaboration
Collaborate closely with software engineers, data scientists, analytics professionals, and business stakeholders.
Develop reusable analytics frameworks, AI components, and best practices.
Support deployment, ongoing optimization, and adoption of AI-powered analytics solutions.
Required Qualifications
7+ years of experience in AI Engineering, Analytics Engineering, Data Engineering, Software Engineering, Solution Architecture, or a related field.
Proven experience building analytics, reporting, dashboarding, or decision-support solutions.
Experience designing, developing, and deploying LLM-enabled applications in production environments.
Strong understanding of semantic modeling, business metrics, and data interpretation.
Experience with RAG architectures and agentic AI systems.
Strong stakeholder-facing discovery, consulting, and problem-solving skills.
Demonstrated ability to translate business questions into technical solutions.
Strong Python development and backend engineering experience.