About the job
We are seeking a Principal Agentic Data Systems Engineer. This is a role for a technical visionary who has mastered traditional data engineering and is now focused on the next frontier: Agentic Force Multiplication. In this position, you shift from being a traditional individual contributor to a Human-in-the-Loop (HITL) Orchestrator. You will serve as the primary architect of a high-performing digital workforce, operating as a 'Team of One' that achieves the output equivalent of a 3-5 person engineering squad. Your value lies not in manual coding, but in the high-level design and supervision of autonomous agents that execute engineering, QA, governance, and analytics workflows on your behalf.
Responsibilities
Autonomous Scaling: Architect and maintain a private ecosystem of 10+ autonomous agents specialized in ETL, synthetic data generation, automated QA, and predictive modeling.
Agentic Orchestration: Design multi-step reasoning architectures and verification protocols to ensure agents autonomously validate and peer-review their own outputs.
Complex Problem Resolution: Transform high-level, ambiguous business requirements into production-ready data products independently, bypassing the need for mid-level project management.
Governance & Oversight: Use domain knowledge to ensure deployed tools are well governed. Governance as code for data pipelines and Agentic development. Context aware Agent development.
Contextual Integration: Develop and maintain Model Context Protocol (MCP)
Qualifications
Minimum
Experience: 7+ years of experience in high-stakes Data Engineering, Architecture, or Data Science.
Operational Leverage: A documented history of using generative AI to accelerate personal and departmental output by orders of magnitude.
Strategic Autonomy: The ability to function as a 'Domain Data Officer,' managing end-to-end data strategy for a business unit with minimal supervision.
Technical Intuition: Superior analytical judgment—the ability to identify subtle logic errors or hallucinations in agentic output before they reach production.
Preferred
Engineering Foundation: Production-grade proficiency in Python, dbt, Airflow, and advanced SQL. Apache Spark, and Snowflake.
AI Orchestration: Fluency in AI-native development environments (e.g., Cursor, Codex, or Claude Code). Expert in Prompt Engineering. Mastery of agentic frameworks such as LangGraph. Leverage MCP servers to retrieve data from tool stack
Cognitive Architecture: Expert-level knowledge of chain-of-thought prompting, self-correction loops, and iterative reasoning paths.
Salesforce Knowledge: Salesforce Core and Data 360 understanding
Systems Design: Advanced understanding of Data Mesh, Data-as-a-Product (DaaP), and Event-Driven Architectures. Semantic layer. Knowledge Graphs.
Cloud Infrastructure: Experience using agentic workloads via Docker, Kubernetes, and serverless compute environments.