GCP Data Pipeline Engineer

Our Client is looking for a GCP Data Pipeline Engineer. This is a 100% Remote role. Please find the detailed job requirement, if interested kindly reply back with your updated resume and contact info.Role Overview: GCP Data Pipeline EngineerLocation: US/Canada PreferredDuration: 6 months Experience & Core Tech: 8+ years of experience designing and building scalable batch and real-time data pipelines using Python, Airflow, and Snowflake (including advanced SQL and performance tuning).Enterprise Data Ingestion: Proven expertise in API and file-based ingestion, handling both structured and unstructured data (PDFs, TIFFs, Docs) from core business systems like Gmail, GDrive, GCalendar, GChat, Zoom, Slack, oneDrive, Evernote, Advanced AI & LLM Data Prep: Hands-on experience orchestrating Multi-Modal LLM APIs (e.g., Gemini, GPT-4V) for OCR and document parsing. Must understand token-aware chunking and staging data for Vector databases and Knowledge Graphs (supporting AI-powered legal query systems).Data Quality & Validation: Ability to drive data observability and apply AI output validation techniques (readability scoring, confidence thresholds, fallback logic) to ensure high-quality downstream consumption.DevOps, Security & Compliance: Strong alignment with DevOps/CI/CD practices, data encryption standards (PGP, SFTP, GCS), and data privacy regulations relevant to litigation data handling.Education & Soft Skills: Bachelor s or Master s degree in Computer Science or a related field, paired with the communication skills needed to bridge the gap between technical execution and strategic business goals.WE ARE AN EQUAL OPPORTUNITY EMPLOYER