GCP & Python (with Document AI)

Job Description: You will be responsible for designing, deploying, and maintaining automated invoice extraction pipelines using GCP Document AI. Additionally, you will develop custom model training workflows for documents with non-standard formats, preprocess and upload document datasets to Cloud Storage, label documents for training, and integrate extracted data into downstream tools like BigQuery and ERP systems. Your role will also involve writing robust Python code for end-to-end orchestration and maintaining CI/CD deployment pipelines to ensure secure document handling and compliance with data policies. Key Responsibilities: - Design, deploy and maintain automated invoice extraction pipelines using GCP Document AI. - Develop custom model training workflows for documents with non-standard formats. - Preprocess and upload document datasets to Cloud Storage. - Label documents using DocAI Workbench or JSONL for training. - Train and evaluate custom processors using AutoML or custom schema definitions. - Integrate extracted data into downstream tools (e.g., BigQuery, ERP systems). - Write robust, production-grade Python code for end-to-end orchestration. - Maintain CI/CD deployment pipelines. - Ensure secure document handling and compliance with data policies. Required Skills & Experience: - Strong hands-on experience with Google Cloud Platform, especially Document AI, Cloud Storage, IAM, Vertex AI (preferred), Cloud Functions / Cloud Run. - Proficiency in Python, including Google Cloud SDK libraries. - Familiarity with OCR and schema-based information extraction. - Understanding of security best practices for handling financial documents. Preferred Qualifications: - Previous projects involving invoice or document parsing. - Familiarity with BigQuery for analytics/reporting.,