Lead AI Conversational Data Engineer (GCP)

Tasks

• Design and develop customer-specific synthetic data generation pipelines.
• Build and maintain RAG and knowledge ingestion pipelines.
• Generate synthetic conversations, FAQs, knowledge-base articles, and customer/agent profiles.
• Ensure data quality, retrieval accuracy, and privacy compliance.
• Automate data generation, ingestion, and indexing workflows.
• Collaborate with Conversational AI and DevOps teams.

Requirements

• 10+ Years
• Strong hands-on experience in Google Cloud Platform (GCP).
• 10+ years of overall Data Engineering experience.
• 3+ years of experience in Conversational AI / Generative AI / Agentic AI.
• Hands-on experience with RAG (Retrieval-Augmented Generation) pipelines.
• Expertise in Synthetic Data Generation using LLMs.
• Experience creating synthetic conversation datasets for voice and chat applications.
• Knowledge of CCAI training and evaluation datasets.
• Experience building data ingestion, processing, and indexing pipelines.
• Familiarity with BigQuery, AWS S3, and document-based knowledge repositories.
• Understanding of NLP, data quality, PII detection, and privacy compliance.
• Experience with multilingual data generation and evaluation is a plus.

Schedule

• Duration: 3–6 Months

How to apply

• Share your updated resume by email.

Location

• Minneapolis, MN, USA