Founding Analytics Engineer

From volatile markets to climate shifts, independent operators face mounting pressure. While sustainable investments often yield the best long-term returns, they require financial clarity and capital that fragmented legacy systems can’t provide.

• The entire data layer downstream of production databases — warehouse, dbt models, Airbyte pipelines, orchestration — plus primary company-wide dashboards, data access patterns for AI agents, and an advisory role on data modeling in external systems (e.g., HubSpot) to keep upstream data clean.

• Data literacy across the company — how to think about metrics, write better queries, and self-serve in Hex. Best practices for structuring data in the tools teams own. Metrics definitions and consistency so the team asks the right questions of the data.

• The data model. Grow our capacity by resolving gotchas, improving documentation, and building trust. Enable teams to self-serve on reliable data.

• Get deep into Ambrook's business model, product, and customers to understand how we make money and who we serve.

• Trace the full data lineage from product databases through Airbyte into the warehouse to understand the plumbing and where things can break.

• Audit the existing warehouse schema, dbt models, and Hex dashboards; document the known gotchas and tribal knowledge.

• Meet with Growth, Ops, CS, Product, and Engineering to understand their data needs and pain points.

• Own the primary company-wide dashboards — have audited, corrected, and taken accountability for the core dashboards the whole company relies on.

• Begin evolving the data model — started refactoring dbt models to address the highest-priority gotchas and quality issues identified in month one.

• Establish a plan for agent data access — define clean naming conventions, clear data access patterns, and a recommendation on what level of data LLMs should be able to query (raw vs. curated semantic layer.)

• Stood up initial systems that enable teams to self-serve with confidence. The team has processes and tools to unblock themselves with occasional intervention.

• Deliver a significantly improved data model with well-documented models and a meaningfully more trustworthy warehouse.

• Have agent data access operational or in progress with a clean semantic layer or access patterns in place so LLMs can pull data reliably.

• Actively educate the team on data concepts through documentation, 1:1s, and workshops so the team becomes more data-literate and self-sufficient.

• Shape the future of the data function — actively evaluate how AI is changing the data stack and make recommendations on how Ambrook's infrastructure should evolve.

• Proven experience as a solo or early data hire. You've owned the full stack and built infrastructure or the function from scratch.

• Advanced SQL and production dbt, with hands-on experience in a cloud warehouse (BigQuery or similar) and ETL tools (Airbyte or comparable.)

• Strong business instincts. You translate ambiguous questions into clean data models and communicate findings clearly to non-technical teammates.

• Comfortable in fast-moving environments with high-volume sales funnels.

• AI-native approach to data work. You think in terms of agent automation (quality checks, column generation, automated reviews) and actively use AI tools to move faster.

• Bonus: Experience with Airbyte, Hex, and/or BigQuery.

• Bonus: Experience with Airflow or Dagster for orchestration.

• Bonus: Basic ML or statistical modeling experience.