Principal Agentic Data Systems Architect

Own Company; Ciudad de México; Híbrido; MXN 900.000 - 1.300.000; Jornada completa

Descripción de la vacante

Own Company seeks a Principal Agentic Data Systems Engineer to lead the design and governance of autonomous AI-driven data workflows. You will shift from traditional data engineering to orchestrating a team of AI agents handling ETL, QA, and analytics with minimal supervision.

You will implement high-level architectures using Python, SQL, and modern data platforms, ensuring scalable, governed data products across hybrid environments.

Formación

• 7+ years of experience in high-stakes Data Engineering, Architecture, or Data Science.

Responsabilidades

• Autonomous Scaling: Architect and maintain a private ecosystem of 10+ autonomous agents for ETL, synthetic data generation, automated QA, and predictive modeling.
• Agentic Orchestration: Design multi-step reasoning architectures and verification protocols for autonomous validation and peer-review of outputs.
• Complex Problem Resolution: Translate high-level business requirements into production-ready data products independently.
• Governance & Oversight: Governance as code for data pipelines and Agentic development with context-aware tooling.
• Contextual Integration: Develop Model Context Protocol servers for secure data access across Snowflake, Salesforce, AWS, and internal catalogs.

Conocimientos

Python

SQL

dbt

Airflow

Apache Spark

Snowflake

Kubernetes

Docker

LangGraph

Prompt engineering

MCP servers

Salesforce

Data Mesh

DaaP

Event-Driven

Educación

7+ years experience in Data Engineering/Architecture/Data Science

Herramientas

Snowflake

Tableau

dbt

Airflow

Docker

Kubernetes

Spark

Descripción del empleo

Own Company seeks a Principal Agentic Data Systems Engineer to lead the design and governance of autonomous AI-driven data workflows. You will shift from traditional data engineering to orchestrating a team of AI agents handling ETL, QA, and analytics with minimal supervision.

You will implement high-level architectures using Python, SQL, and modern data platforms, ensuring scalable, governed data products across hybrid environments.