Job Title: GCP Architect Engineer (Document Processing)Location: Atlanta, GA
Job Overview:We are seeking a
GCP Architect Engineer with expertise in document processing technologies and a deep understanding of Google Cloud Platform (GCP) services, particularly
Vertex AI and
AlloyDB. The ideal candidate will have experience handling complex document workflows involving PDF and HTML formats, building scalable architectures for document management, and applying advanced AI/Client techniques, including
LLMs and
OpenAI GPT, for data extraction, processing, and analysis.
Key Responsibilities: - Design and architect end-to-end document processing pipelines using GCP services.
- Implement scalable solutions for PDF, HTML, and other document formats, ensuring efficient extraction and processing of data.
- Leverage Vertex AI, AlloyDB, and BigQuery to develop, deploy, and optimize machine learning models for document processing tasks, such as text extraction, classification, and analysis.
- Collaborate with product and engineering teams to translate business requirements into scalable GCP architecture.
- Lead the design and integration of automated document workflows using GCP services like Cloud Storage, Cloud Functions, Pub/Sub, and BigQuery.
- Ensure the document processing system is robust, reliable, and capable of handling high-volume workloads.
- Optimize document storage, retrieval, and search functionalities to enhance efficiency and performance.
- Provide technical leadership in developing strategies for document digitization, data extraction, and machine learning in document handling.
- Troubleshoot performance issues and continuously improve system architecture and efficiency.
Required Qualifications: - 5+ years of experience as a Cloud Architect or Cloud Engineer working with Google Cloud Platform (GCP).
- Expertise in document processing technologies, including experience with PDF, HTML, and other document formats.
- Experience with Vertex AI, Vertex DB, AlloyDB, and BigQuery for building AI-driven document processing solutions.
- Strong knowledge of GCP services such as Cloud Storage, Cloud Functions, BigQuery, Dataflow, and Pub/Sub.
- Proven ability to design and implement scalable document processing architectures in GCP.
- Proficiency in Python, Java, or other relevant programming languages used for document parsing and processing.
- Experience with natural language processing (NLP) techniques, optical character recognition (OCR), and data extraction from unstructured documents.
- Strong understanding of cloud infrastructure, distributed systems, and data management principles.
- Experience with LLMs such as OpenAI GPT, Google Gemini, and Anthropic Claude (future) for advanced AI/Client document processing tasks.
- Knowledge of Google Medpalm for healthcare-related document processing solutions.
Preferred Qualifications: - Experience with automation of document workflows and integration of AI/Client-based solutions for data extraction and processing.
- Familiarity with metadata extraction, information retrieval, and search optimization in document management systems.
- Knowledge of HTML parsing and handling complex document formats.
- Experience working in an Agile environment and collaborating with cross-functional teams.
