Data Engineer Senior | AI & Data
Salary not listed • Mexico - Mexico City • Full-time
Posted 12d ago
About the job
Salesforce is seeking a Senior Data Engineer to join their AI & Data team in Mexico City. This role involves designing, building, and optimizing scalable data pipelines and models that power analytics, AI, and business insights. You will work with modern data platforms and leverage AI-native development tools and agentic workflows to enhance development speed, validation rigor, and data product reliability. The position focuses on building and maintaining automated pipelines, integrating data from various systems, ensuring data accuracy and consistency, and partnering with cross-functional teams to deliver production-ready data products. A key aspect of the role includes building agentic workflows for ETL, QA, anomaly detection, and pipeline remediation, along with designing verification patterns for agent output.
Responsibilities
- Design, build, and maintain automated data pipelines and dimensional/star/snowflake models using dbt, Snowflake, Informatica, and Airflow.
- Integrate data from multiple systems, including Salesforce Core and Data 360, into unified, high-quality datasets.
- Ensure data accuracy, completeness, and consistency through validation, observability, and automated monitoring.
- Troubleshoot data issues and optimize pipelines for performance, scalability, and cost.
- Partner with analysts, product managers, and business teams to translate requirements into data products.
- Utilize AI-native tools (e.g., Cursor, Codex, Claude Code) to accelerate development, testing, documentation, and troubleshooting.
- Build agentic workflows for ETL, automated QA, anomaly detection, and pipeline remediation, including reviewing and approving agent-proposed fixes.
- Design verification patterns (self-correction loops, peer-review agents, human-in-the-loop checkpoints) to validate agent output before production.
- Develop MCP servers for secure, governed access to data sources for agents and use agents to maintain documentation, lineage, and metadata.
- Supervise long-running agent tasks with checkpoints, cost controls, and audit trails.
- Contribute to agent-assisted modeling and simulation workflows.
- Apply governance as code to pipelines and agents, including lineage, access controls, semantic definitions, and audit logging.
- Support data quality and governance initiatives.
- Contribute to red-team and validation agents to identify logic flaws, vulnerabilities, and integrity risks in pipelines and agents.
- Lead and mentor peers on AI-assisted engineering practices.
- Improve tools, standards, and documentation.
- Evaluate emerging data and AI technologies.
Requirements
- 5–7 years of hands-on data engineering experience.
- Strong data modeling skills (dimensional, star/snowflake) and data curation experience.
- Production experience with dbt and Snowflake.
- Working knowledge of Informatica and Airflow.
- Proven use of AI coding assistants and generative AI to deliver measurably faster results.
- Hands-on context engineering and agent design (tool use, reasoning, self-correction).
- Ability to identify logic errors and hallucinations in AI-generated output.
- Strong problem-solving skills.
- Attention to detail.
- Cross-functional communication skills.