Senior Data Engineer – Customer AI Analytics

United Airlines•Chicago, IL

1d•$117,610 - $153,146

About The Position

United's Digital Technology team is comprised of many talented individuals all working together with cutting-edge technology to build the best airline in the history of aviation. Our team designs, develops and maintains massively scaling technology solutions brought to life with innovative architectures, data analytics, and digital solutions. We are seeking a highly skilled Senior Data Engineer to join our Retail AI Automation team. This role is critical in transforming massive volumes of conversational data, customer interaction logs, and AI agent performance metrics into actionable business insights that drive continuous improvement of our AI automation capabilities. Our Vision: We are giving our people the backup they've always deserved, so that when a customer needs a human, they get the most outstanding customer experience they can imagine from AI. You will be building the data infrastructure and analytics capabilities that measure, optimize, and prove the value of AI automation at scale. You will be responsible for designing and building robust data pipelines that process millions of customer conversations, creating analytics data products that enable business stakeholders to understand AI performance, customer behavior, and operational impact across voice, chat, and future channels.

Requirements

Bachelor's degree in Computer Science, Data Engineering, Information Systems, or related field preferred
3+ years of hands-on experience designing, optimizing, and maintaining large-scale data processing workloads
Expert-level proficiency in PySpark and Databricks (DataFrames, Structured Streaming, Delta Lake)
Advanced SQL skills with deep expertise in writing and optimizing complex, high-volume queries
Experience with cloud data platforms, preferably AWS (Redshift, S3, Glue, Athena)
Proven track record of parsing and structuring complex, semi-structured data (JSON, nested structures, logs)
Strong understanding of analytics data modeling and dimensional design principles
Experience building data pipelines that support business intelligence and reporting use cases
Proficiency with PowerBI or similar visualization tools for exposing data products to business users
Self-starter mentality capable of auditing unfamiliar schemas, reverse-engineering logic, and delivering production-ready solutions with minimal guidance
Must be legally authorized to work in the United States for any employer without sponsorship
Successful completion of interview required to meet job qualification
Reliable, punctual attendance is an essential function of the position

Nice To Haves

Master's degree in Computer Science, Data Science, or related field
Experience processing conversational data, chat logs, voice transcripts, or customer interaction data
Familiarity with AI/ML telemetry, LLM prompt/response data, or agent orchestration logs
Experience building analytics for AI systems including performance monitoring, accuracy measurement, and impact analysis
Knowledge of natural language processing (NLP) concepts and text analytics
Experience with real-time streaming data processing and event-driven architectures
Familiarity with data quality frameworks and automated testing for data pipelines
Experience with contact center analytics, customer journey analytics, or operational efficiency metrics
Understanding of how to map system performance data to business outcomes and customer experience metrics
Prior experience in travel, e-commerce, retail, or customer service industries
Experience working in fast-paced, enterprise-scale environments with complex data ecosystems
Knowledge of data governance, privacy regulations, and responsible AI data practices
Familiarity with Agile/Scrum methodologies and collaborative development practices

Responsibilities

Transform raw conversational data, AI agent logs, and customer interaction events into structured, reliable analytics data assets
Design and build scalable data models that support AI performance monitoring, customer journey analytics, and business impact measurement
Create reusable data products that enable self-service analytics for business stakeholders, data scientists, and AI engineers
Build highly optimized, modular PySpark pipelines within Databricks to process large-scale conversational data and AI telemetry
Convert ad-hoc analytical queries into production-ready data pipelines with rigorous testing and monitoring
Implement incremental processing patterns and Delta Lake optimization techniques to minimize compute costs and improve query performance
Parse and structure complex, semi-structured conversational data including chat transcripts, voice call logs, AI agent decision traces, and customer intent classifications
Standardize ingestion of diverse data sources including LLM prompt/response pairs, agent orchestration logs, and customer feedback signals
Build precise conversation funnel metrics, AI containment rates, resolution accuracy, and customer satisfaction analytics
Design data models that enable comprehensive AI agent performance monitoring including response accuracy, latency, escalation patterns, and customer satisfaction
Create analytics frameworks that measure business impact of AI automation including cost savings, wait time reduction, and operational efficiency gains
Build attribution logic that connects AI interactions to downstream business outcomes such as bookings, customer retention, and contact center volume reduction
Enforce rigorous technical standards across all data products including schema enforcement, data quality validation, and comprehensive metadata documentation
Implement standardized naming conventions, data lineage tracking, and documentation practices
Ensure data products meet security, privacy, and compliance requirements for customer interaction data
Expose Databricks Delta tables to PowerBI and other visualization tools for business stakeholder consumption
Partner with business analysts and product managers to design intuitive dashboards and reports that drive decision-making
Create automated reporting frameworks that deliver regular insights on AI performance and business impact
Transition experimental analytics work into robust, production-ready data assets with comprehensive monitoring and alerting
Partner with analytics teams, AI engineers, and business stakeholders to ensure data products meet evolving business needs
Document data products thoroughly to enable handoff to broader engineering teams for long-term maintenance