AI Analytics Engineer

About the role

This role owns the complete lifecycle of AI agents embedded within critical business functions, driving them from initial problem framing through reliable production deployment. The hire will ensure every agent delivers tangible value by identifying high-impact opportunities and removing workflow friction. They will act as the primary owner for execution standards, raising the bar for what AI can achieve in this organization. Success requires close collaboration with domain experts to translate complex requirements into robust technical solutions. The position is centered on measurable outcomes, ensuring each deployment generates clear business impact in terms of efficiency, cost, or revenue.

Key facts

What you'll do

• Ship production-grade AI Agents by identifying workflow bottlenecks and iterating through rigorous testing to achieve stable deployment with active user adoption and documented quantitative impact such as time saved or cost reduced.
• Architect and maintain a Self-Serve Operations Framework by creating comprehensive documentation for every deployed agent immediately after launch, covering inputs, outputs, failure modes, and remediation steps to empower any teammate to operate or modify it independently.
• Conduct structured Discovery Sessions with key stakeholders in the embedded function to build a living, prioritized opportunity backlog that scores problems by friction level, technical feasibility, and potential impact.
• Drive Continuous Improvement for deployed solutions by monitoring real-world performance, detecting anomalies, and implementing enhancements validated through measurable gains in reliability, adoption, or output quality in the short term after launch.
• Design data models that are inherently AI-friendly, ensuring schemas and transformations are understandable, maintainable, and extensible by intelligent agents with minimal human intervention.
• Accelerate development cycles by leveraging AI tools to write, validate, and document SQL logic and data transformations, integrating these practices into the standard engineering workflow.
• Define clear specifications for data pipelines and AI behavior before coding, using tools like Claude Code or LiteLLM to translate requirements into executable pipelines where AI serves as the primary execution layer.
• Own the end-to-end delivery of data pipelines, including building robust ELT and ETL processes with AI orchestration, integrating intelligent transformations and anomaly detection directly into production systems.
• Partner closely with the embedded team to act as a trusted advisor, translating complex business problems into technical solutions that drive adoption and demonstrate clear value.
• Establish and monitor key performance indicators for every agent and pipeline, ensuring that improvements are quantifiable and contribute directly to the strategic goals of the business.

Requirements

• Proven experience in SQL and data modeling accelerated with AI, including designing data structures that AI systems can effectively understand, evolve, and maintain over time.
• Strong SQL capabilities for querying and transforming large datasets, using artificial intelligence to accelerate logic validation, testing, and automated documentation of data transformations.
• Demonstrated experience applying AI-assisted testing and data quality validation as a mandatory part of the standard development lifecycle to ensure robustness.
• Demonstrated experience building Python applications and automations that connect intelligent agents with backend data systems and production services.
• A track record of delivering Python-based pipelines or autonomous AI agents that operate reliably in production environments with real users.
• Experience building data pipelines with a specification-first mindset, where clear documentation of inputs, outputs, transformations, and quality checks is created before any code is written.
• Comfort using modern AI development tools such as Claude Code or LiteLLM and the ability to showcase how these tools have compressed delivery timelines for data initiatives.
• Hands-on experience with modern ELT and orchestration frameworks like dbt and Airflow, including the ability to own the complete lifecycle of data pipelines.
• Proven experience integrating AI capabilities into production data pipelines, such as intelligent column transformations, automated anomaly detection, or dynamic workflow automation.
• Extensive experience with data warehouses and AI-native querying patterns, enabling efficient analysis and agent-driven insights at scale.