Santex is a US-based global company founded in 1999, with 26 years of experience in the software industry. Headquartered in California with offices in Córdoba, Argentina, its talent network spans over 18 countries thanks to its flexible, remote-first culture. Santex specializes in custom enterprise software development, operating through Hubs that include eCommerce, BIM, Mobility, Content Delivery, Integration, Web & Mobile Development, Cloud Computing, Artificial Intelligence (AI), Data Science, IT Consulting, and Services. The company is committed to making a positive impact across three dimensions: economic, social, and environmental.
Job Description:
We are seeking an AI Enablement Engineer to design and scale the semantic layer that turns raw restaurant data into a shared language for AI, analytics, and decision-making across a global Quick Service Restaurant (QSR) enterprise. This is a foundational role in our AI strategy: the semantic layer you build is what makes natural language analytics, automated reporting, and intelligent AI agents possible at enterprise scale. Your focus is bridging business meaning and data, ensuring that AI systems, analytics platforms, and end users consistently interpret critical metrics like same-store sales, speed of service, traffic, and labor productivity in a standardized, governed way. When an AI agent or a franchisee asks "how did my restaurant perform last week," the accuracy and trust of that answer starts with your work.
You will define and operationalize a hybrid semantic layer strategy that combines governed, metadata-driven models with AI-powered context engineering to enable scalable, accurate, and self-service insights across restaurants, corporate teams, and franchisees, unlocking the building blocks for conversational analytics and autonomous AI workflows.
Key Responsibilities – Semantic Layer Strategy & Architecture
- Define and implement an enterprise semantic layer that standardizes metric definitions and aligns business questions to data
- Establish canonical definitions for core KPIs (e.g., same-store sales, speed of service, traffic, labor productivity)
- Design mapping between business concepts and underlying data models across systems (POS, digital, supply chain, finance)
- Provide structured metadata to power AI systems, copilots, and analytics tools.
Key Responsibilities – Hybrid Semantic Model Implementation
- Build and maintain manual, metadata-driven semantic models for high-criticality domains (finance, core KPIs, franchise reporting)
- Enable AI-driven context engineering for exploratory analytics, operational insights, and ad-hoc queries
- Define how both approaches coexist in a unified architecture
Key Responsibilities – Tooling & Platform Enablement
- Implement semantic layer tooling (DBT, semantic views, YAML/Markdown metadata, data catalogs like Atlan)
- Enable downstream consumption by BI tools, APIs, and AI applications
- Create reusable abstractions and templates to scale globally
Key Responsibilities – AI & Context Engineering Integration
- Enable AI systems (LLMs, agents, copilots) to leverage semantic metadata
- Support context engineering using data lineage, metadata, example queries, and repository context
- Improve AI reliability by grounding outputs in governed definitions
Key Responsibilities – Governance & Data Quality
- Establish governance processes for metric definitions
- Ensure alignment across regions, brands, and franchise reporting
- Implement validation, versioning, and change management
- Define guardrails to prevent inaccurate analytics outputs
Key Responsibilities – Adoption & Enablement
- Partner with business and technical teams to drive adoption
- Educate stakeholders on standardized metrics and self-service analytics
- Provide documentation, playbooks, and training
Required Qualifications
- Bachelor’s or Master’s degree in Computer Science, Data Engineering, Analytics, or related field
- 5+ years of experience in data engineering, analytics engineering, or AI/ML systems
- Strong experience with semantic modeling or analytics engineering
- Proficiency in SQL and Python
- Experience with DBT and modern cloud data platforms
- Understanding of APIs and distributed systems
Preferred Qualifications
- Experience in QSR, retail, or franchise environments
- Experience with semantic/metrics layers
- Familiarity with data catalogs (e.g., Atlan)
- Experience with generative AI, LLMs, and context engineering
- Knowledge of data lineage and governance frameworks
Additional Expectations
- Design and maintain CI/CD pipelines, including automated builds, testing, and deployment of solutions
- Develop and execute functional and regression test suites to validate metric accuracy, data completeness, and semantic model behavior across environments
- Implement automated data and code quality checks and integration tests within the deployment pipeline to catch issues before they reach production
- Apply software engineering best practices including version control, code review, branching strategies, and environment promotion (dev/staging/prod) to all semantic layer and metadata assets
- Monitor platform performance, troubleshoot pipeline failures, and maintain observability across semantic layer infrastructure using logging, alerting, and health checks
- Define and manage infrastructure as code (e.g., Terraform, CloudFormation) for data platform resources, ensuring reproducible and auditable environment provisioning across development, staging, and production
- Implement and maintain role-based access controls, secrets management, and security policies across semantic layer tooling, data platform resources, and API integrations to ensure compliance with enterprise security standards
Key Skills & Competencies
- Systems thinking across data, analytics, and AI
- Ability to translate business metrics into data models
- Balance governance with scalability
- Strong stakeholder management
- Clear communication of complex concepts
Success Metrics
- Adoption of standardized metric definitions
- Reduction in reporting inconsistencies
- Improved accuracy of AI-generated insights
- Increased self-service analytics usage
- Faster time-to-insight
Reporting Structure
- Reports to: VP / Director of Data, AI, or Platform Engineering
- Works closely with: Data Engineering, Analytics, AI/ML, Finance, Operations, Franchise teams
Summary
The AI Enablement Engineer (Semantic Layer) establishes a shared language between business and data. By combining governed semantic models with AI-driven context understanding, this role enables scalable, accurate, and trusted analytics and AI across a global QSR enterprise.
Location: LATAM