Conversational Data Engineer
100% Remote Role
Client:UHG
Remote
Job Requirements
Experience: 7–10 years
Minimum Relevant Experience: 4+ years
Primary Focus: Conversational AI, Synthetic Data, RAG/Knowledge Pipelines, NLP, Data Engineering
Cloud Platforms: GCP and AWS
Role Summary
We are looking for an experienced Conversational Data Engineer to create high-quality, customer-specific synthetic data and own RAG/knowledge pipelines supporting CCAI, voice, and chat deployments.
The engineer will design scalable data generation and ingestion pipelines and load data into the appropriate GCP and AWS services. The role requires a strong understanding of conversational AI data, knowledge management, retrieval systems, synthetic data generation, and data privacy.
The goal is to enable each customer deployment to be configured, grounded, demonstrated, and validated without using real customer PII.
What Success Looks Like
Each customer engagement has a documented synthetic dataset covering all channels within scope.
Each in-scope customer has a functional RAG/knowledge pipeline, including:
Corpus preparation
Indexing
Retrieval
Evaluation
Data and retrieval quality are sufficient for:
Configuration
Evaluation and testing
Stakeholder demonstrations
Synthetic data meets privacy, isolation, and compliance expectations.
Data generation and indexing processes are parameterized, repeatable, and scalable, rather than manual, one-off processes.
Key Responsibilities
Synthetic Data Generation
Analyze each customer's domain, including:
Intents
Entities
Knowledge topics
Document types
Languages
Tone
Edge cases
Generate synthetic conversation transcripts for voice and chat.
Create synthetic CCAI training and evaluation dialogues.
Generate supporting content, including:
Customer and agent profiles
Knowledge-base articles
FAQs
Structured entity values
Select appropriate synthetic-data generation techniques and document parameters, assumptions, and limitations.
RAG & Knowledge Pipelines
Design and maintain RAG and knowledge ingestion pipelines.
Prepare, transform, index, retrieve, and evaluate customer-specific knowledge corpora.
Load data into the appropriate GCP and AWS services.
Schedule and document index-refresh processes when customer knowledge changes.
Ensure data and indexes are correctly integrated into deployed conversational experiences.
Data Quality & Privacy
Validate synthetic data for:
Realism
Coverage
Diversity
Consistency
Retrieval quality
Verify the absence of residual real-world PII in synthetic datasets and source corpora.
Ensure data meets appropriate privacy, isolation, and compliance requirements.
Develop and maintain reusable data-quality checklists.
Automation & Reusability
Build and maintain reusable:
Synthetic-data generators
Data ingestion jobs
Indexing pipelines
Quality-validation processes
Parameterize pipelines to support different customers and use cases.
Minimize manual, customer-specific copy-paste processes through automation and repeatable workflows.
Collaboration
Partner with the Conversational Platform Specialist to ensure loaded data and indexes effectively support the deployed conversational experience.
Partner with DevOps to automate:
Pipeline jobs
Data stores
Secrets management
Ensure pipeline jobs, data stores, and other resources are properly isolated for each customer.
Required Qualifications
4+ years of experience in one or more of the following:
Data Engineering
Conversation Design Operations
Applied NLP Data
Knowledge-Pipeline Engineering
Working knowledge of how conversational platforms consume:
Training data
FAQs
Conversation transcripts
Retrieval-grounded knowledge
Strong understanding of synthetic-data quality and generation.
Strong understanding of RAG and retrieval quality.
Strong judgment regarding data privacy, PII protection, and security.
Experience designing or maintaining data generation and ingestion pipelines.
Experience working with cloud-based data platforms, particularly GCP and/or AWS.
Preferred Qualifications
Experience with LLM-assisted synthetic data generation in a production or customer implementation environment.
Familiarity with:
Google BigQuery
Amazon S3
Document stores used as knowledge sources
Experience with RAG, vector search, semantic search, knowledge retrieval, or indexing.
Experience with multilingual data generation or evaluation.
Experience supporting conversational AI, voice, chat, or CCAI platforms.
Experience working on enterprise or customer-specific implementations.
Key Skills
Conversational AI | Synthetic Data | RAG | Knowledge Pipelines | NLP | LLMs | CCAI | Data Engineering | BigQuery | AWS S3 | GCP | AWS | Data Ingestion | Indexing | Knowledge Base | Data Quality | PII Protection | Multilingual Data

Remote Role :: Conversational AI Data Engineer

Similar Engineering Jobs

Machine Learning Developer

Senior Data Engineering & Platform Engineer (DBT)

Hadoop Data Engineer - Scottsdale AZ (100% Onsite)

Sr. Full Stack Data AI Engineer – GCP & Agentic AI

Full-Stack Engineer – Data Experience, Backstage Portal [SK-17196]

Solutions Analyst & Engineer