Lead Data Systems EngineerMexico City | Full-TimeHybridThe Enterprise Data & AI Solutions group is the organization's strategic hub for cognitive automation. We move beyond traditional data management to build the autonomous engines that power executive decision-making. We are seeking a Lead Agentic Data Systems Engineer.This is a role for a hands-on, depth-first engineer who will take the architectural blueprints set by our Principal Engineers and turn them into hardened, production-grade data products. You will own the product end-to-end — building it, maintaining it, enhancing it, and constructively challenging the design when implementation reality demands it. You are the person the business trusts to make a data product actually work, at quality, every day. The Strategic Shift: You are redefining the data team model. Instead of managing human personnel, you manage complex "hand-off" protocols between specialized AI agents, acting as the central anchor for a hybrid human-agent intelligence unit.Architect and maintain a private ecosystem of 10+ autonomous agents specialized in ETL, synthetic data generation, automated QA, and predictive modeling.Transform high-level, ambiguous business requirements into production-ready data products independently, bypassing the need for mid-level project management.Governance as code for data pipelines and Agentic development. Develop and maintain Model Context Protocol (MCP) servers to provide agents with secure, deep-link access to Snowflake, Salesforce, AWS, and proprietary internal data catalogs.Engineering Foundation: Production-grade proficiency in Python, dbt, Airflow,



and advanced SQL. Apache Spark, and Snowflake.Expert in Prompt Engineering. Leverage MCP servers to retrieve data from tool stackSalesforce Knowledge: Salesforce Core and Data 360 understandingAdvanced understanding of Data Mesh, Data-as-a-Product (Daa P), and Event-Driven Architectures. Cloud Infrastructure: Experience using agentic workloads via Docker, Kubernetes, and serverless compute environments.Experience: 5+ years of experience in high-stakes Data Engineering, Architecture, or Data Science.Strong Python / SQL ExpertiseStrategic Autonomy: The ability to function as a "Domain Data Officer," managing end-to-end data strategy for a business unit with minimal supervision.While you start your day, your "Scout Agents" have already completed an automated audit of the overnight data pipelines. You review a synthesized report highlighting three anomalies in the global revenue stream. One agent has already drafted a proposed SQL remediation and a unit test; you review the logic and authorize the deployment to production.Stakeholder triage and problem framing/overnight pipeline audit, anomalies, drafted SQL remediation, unit test, approve deployment:Snowflake, Tableau metadata, dbt artifacts,



pricing event logsA request arrives from the CFO for a "High-Resolution Market Volatility Stress Test." You deploy an "Information Retrieval Agent" to parse thousands of historical Slack threads, Jira tickets, and Git Hub commits. You direct the agent to update the general metadata repository so this knowledge is permanently accessible to the organization.legacy algorithm overview/chage, retrieval across historical Slack / Jira / Git Hub, technical summary, metadata repository update.search across SQL corpus, dbt lineage, notebook agentsdrafted explanations and SQL patches15:30 – Defensive Systems EngineeringYou dedicate time to "Security & Integrity Engineering," building new "Red-Team Agents" whose sole purpose is to attempt to find flaws in the logic or security vulnerabilities in your other agents. You are building a self-healing digital immune system for the company's data.Agents prepare modeling and simulation workflows to test strategic scenarios such as pricing or renewal changes. 18:00 – Asynchronous Task DeploymentYou initialize a long-tail analytical task: "Analyze the last 24 months of customer churn data and identify latent correlations that current linear models have missed." You disconnect while the agentic fleet begins the heavy compute and reasoning cycles overnight.20:00+ – Long-Tail Agent Execution After hours, agents continue computationally heavy or long-horizon tasks, creating a curated queue of opportunities, risks, and partially completed work for the next morning.#

📌 Lead Agentic Data Systems Engineer (Ciudad de México)
🏢 Tableau
📍 Ciudad de México