Production ML Engineer in Cape Town
Adrian Zevenster
I build reliable AI systems for documents, knowledge, and decisions.
Production ML, AI, and cloud engineering
My work covers Java and Python services, Vertex AI, Gemini, Document AI, BigQuery, Spanner, Kafka, ClickHouse, Terraform, evaluation, and production observability.
Technical leadership in document verification
Designed page-level processing, multi-source file contracts, document-specific scoring, and regression checks for large document batches.
Read the architecture decisions and implementation evidence.
Selected work
- RedStrings secure generative-media platform with isolated Google Cloud projects, IAP-protected manager and artist workflows, scheduled Drive intake, and exact-media provenance.
- Multi-file KYC document verification with dedicated utility-bill, bank-statement, and financial-report intelligence paths.
- Gemini regression testing with fixture, replay, live-model, and prompt-drift gates.
- A floriculture data and forecasting platform with validated workbook ingestion, BigQuery and Dataform modelling, and nine-level reconciled forecasts on Vertex AI.
- An analytics agent with validated tool calls, retrieval, supervised ML, and explainable results.
- Forecasting, churn, recommendation, migration, and real-time decision systems.