Senior Data & AI Platform Engineer

Overview of the Role

The Senior Data & AI Platform Engineer will own the end-to-end data pipelines supporting the business, bringing client data, documents, call transcripts, and other information into a centralized PostgreSQL platform on GCP. The role also involves supporting Document AI and LLM solutions that process over 90,000 client files. This is a hands-on Data Engineering position focused on building, operating, troubleshooting, and improving reliable production pipelines rather than data warehousing, big data, or ML model development.

Key Responsibilities:

• Own end-to-end production data pipelines, from design and development through deployment, monitoring, troubleshooting, and ongoing maintenance.
• Build and maintain Python-based data ingestion pipelines that pull information from third-party APIs and other sources such as client data, documents, and call transcripts.
• Consolidate data into a centralized PostgreSQL environment, ensuring data is reliable and accessible to downstream business systems.
• Design, develop, and maintain cloud-based data solutions using GCP and/or AWS, with GCP technologies including: Cloud Run, Cloud Functions, Cloud SQL, Pub/Sub, BigQuery, Cloud Scheduler, and Document AI
• Take primary responsibility for investigating and resolving production pipeline failures, data issues, and integration problems.
• Develop and maintain advanced PostgreSQL solutions, including complex/large views, JSONB structures, migrations, roles, grants, and database-level access controls.
• Build and support document-processing and AI/LLM pipelines, including systems capable of processing large volumes of client documents.
• Implement production LLM features and establish methods for evaluating the quality and accuracy of AI-generated outputs where applicable.
• Build or maintain MCP servers/tools that enable AI applications to interact with business data and answer meaningful business questions.
• Design secure, scoped, fail-closed APIs for accessing sensitive financial information, including parameterized queries, server-side identity verification, SQL-enforced authorization, and versioned API contracts.
• Apply appropriate privacy, security, access controls, and auditability when handling sensitive Australian client financial data.
• Work directly with Pivot Wealth's Sydney-based stakeholders, advisers, brokers, and engineering team to understand business requirements and translate them into reliable technical solutions.
• Operate with a high degree of technical ownership and accountability, particularly in a small engineering environment.