Lead AI/ML Engineer (DocAI) - R01557619

AI overview

Design and deploy automated invoice extraction pipelines using GCP Document AI, while developing custom model training workflows for non-standard documents and ensuring secure data handling.

Lead AI/ML Engineer Primary Skills

Problem Formulation (Business problem to Data Science Problem), OKR Validation against statistical measures, Data Wrangling, Data Storytelling & Insight Generation, Problem Solving, Excel VBA, Data Curiosity, Technical Decision Making (How many iterations to go for vs when to stop iterating), Communication & Articulation: Vocal & Written, Business Acumen (Consume new domains quickly to learn through data), Design Thinking, Data Literacy

Job requirements

Job Title: Document AI Engineer

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: o Document AI o Cloud Storage o IAM o Vertex AI (preferred)

· Proficient in Python, including Google Cloud SDK libraries

· Familiarity with OCR, and schema-based information o Cloud Functions / Cloud Runextraction

· Understanding of security best practices for handling financial documents -

-- Preferred Qualifications ·

Previous projects involving invoice or document parsing

· Familiarity with BigQuery for analytics/reporting