Senior Conversational Data Engineer

Sensiple Inc is a New Jersey corporation with over two decades of expertise in technology-driven solutions specializing in Customer Experience, Contact Centre Solutions, Digital Transformation, Cloud Computing & Independent Testing.

With an expert team that has enriched experience in executing & developing sustainable IT strategies in Healthcare, Technology, Retail, Logistics, Education, Telecommunications, Government and Media, we help our diverse customers to envision the future. By developing highly scalable and consistent solutions, our primary goal is to deliver excellence at all levels and delight our customers and drive them to a better future.

One of our clients is looking for a Senior Conversational Data Engineer @Minneapolis, MN please find below the details of the position.

Job Title: Senior Conversational Data Engineer
Location : Minneapolis, MN
Skill: Google Cloud Platform / Generative AI / Data Engineering
Experience: 7–10 years
Duration: 6 months

Job Summary

We are looking for a Senior Conversational Data Engineer to build synthetic datasets and RAG (Retrieval-Augmented Generation) knowledge pipelines for conversational AI, voice, and chat applications.

The candidate will generate realistic, customer-specific synthetic data without exposing real customer Personally Identifiable Information (PII). They will build repeatable data generation, ingestion, indexing, and retrieval pipelines using appropriate Google Cloud Platform and AWS services.

Key Responsibilities

• Generate synthetic voice and chat conversations, training dialogues, FAQs, knowledge-base articles, and customer/agent profiles.
• Design and maintain RAG and knowledge ingestion pipelines for conversational AI applications.
• Prepare, organize, index, and validate documents for retrieval and search.
• Work with BigQuery, Amazon S3, and document stores used as knowledge sources.
• Evaluate synthetic data for quality, realism, diversity, coverage, and privacy compliance.
• Automate and maintain reusable data generation, ingestion, and indexing processes.
• Schedule and document knowledge-base refreshes as customer information changes.
• Collaborate with conversational AI platform specialists and DevOps teams to support deployments, testing, and demonstrations.
• Ensure customer data and pipelines remain isolated, secure, and repeatable.

Required Qualifications

• 4+ years of experience in data engineering, NLP data processing, conversational AI operations, or knowledge pipeline engineering.
• Strong understanding of conversational AI training data, transcripts, FAQs, and retrieval-grounded knowledge.
• Experience working with data generation, ingestion, transformation, and indexing pipelines.
• Knowledge of synthetic data quality, retrieval evaluation, and data privacy.
• Familiarity with Google Cloud Platform services and data engineering concepts.

Preferred Qualifications

• Experience using LLMs to generate synthetic data in production or implementation projects.
• Knowledge of BigQuery, Amazon S3, and document databases or knowledge stores.
• Experience with RAG pipelines, NLP, and conversational AI platforms.
• Multilingual synthetic data generation or evaluation experience.
• Experience building automated and reusable data pipeline