Lead AI Conversational Data Engineer
Parikshith SanaUnited StatesLEADPosted 2h ago
Data EngineeringConversational AIAgentic AIGenerative AIRAG architectureknowledge pipeline developmentLLM-based synthetic data generationVoice and chat conversation datasetsCCAI training/evaluation dataGCP BigQueryAWS S3document storesData ingestionindexingretrievalrefresh pipelinesPII protectiondata privacysynthetic data validation
About the Role
We are seeking a Lead AI Conversational Data Engineer to join our team in Minneapolis, MN. This role involves working with cutting-edge technologies in Conversational AI, Agentic AI, and Generative AI to develop and maintain data pipelines.
Key Responsibilities
• Develop and maintain data pipelines for Conversational AI systems
• Implement RAG architecture and knowledge pipelines
• Generate synthetic data using LLMs
• Manage voice and chat conversation datasets
• Ensure data privacy and PII protection
• Work with GCP BigQuery, AWS S3, and document stores
Requirements
• 15+ years of overall experience
• 3+ years of relevant experience in Conversational AI, Agentic AI, or Generative AI
• Strong hands-on technical expertise in data engineering
• Experience with RAG architecture and knowledge pipeline development
• Proficiency in LLM-based synthetic data generation
• Knowledge of voice and chat conversation datasets and CCAI training/evaluation data
• Experience with GCP BigQuery, AWS S3, and document stores
• Understanding of data ingestion, indexing, retrieval, and refresh pipelines
• Experience with PII protection, data privacy, and synthetic data validation