Data Engineer - AI-Enabled Capacity Analytics

Comcast’s National Traffic and Capacity Management team is hiring a Data Engineer III to deliver trusted, scalable data capabilities for network capacity planning and optimization.

Responsibilities

• Design, develop, test, deploy, and support scalable data applications, planning tools, APIs, and data pipelines for network capacity planning and analysis.
• Build and optimize ELT and ETL processes across batch and streaming datasets.
• Create automated data-quality checks, anomaly detection, master data management, metadata management, lineage, and monitoring processes.
• Develop, tune, and fine-tune machine learning and AI models; evaluate performance and integrate models into production data applications and workflows.
• Develop automation for recurring workflows, including orchestration, validation, monitoring, and issue notification.
• Optimize and monitor data-intensive processes and applications; identify and resolve performance, scalability, and data-quality issues.
• Provide system documentation.
• Perform ad hoc data analysis and support AI-assisted insight generation.
• Create and maintain clear documentation for data pipelines, software specifications, system designs, processes, and support procedures.
• Apply versioning, testing, privacy protection, cybersecurity, regulation compliance, governance, responsible AI practices, and monitoring for data and AI solutions.
• Collaborate with network engineering, product, operations, software development, and data science partners to translate requirements into reliable technical solutions.
• Adapt quickly to evolving business priorities while balancing multiple initiatives and maintaining solution quality and delivery commitments.
• Proactively identify risks, dependencies, and improvement opportunities; escalate issues early and drive resolutions independently.

Requirements

• 5+ years of relevant experience (listed as 5 to 7 years).
• Strong proficiency in SQL and Python (or similar), with experience in data engineering, data quality, data product development, application development, or data analytics.
• Hands-on experience building production data applications using AWS, Databricks, Spark, or comparable cloud and distributed-processing technologies.
• Deep experience building, monitoring, and optimizing large-scale data pipelines and data-intensive applications.
• Working knowledge of machine learning workflows, including model development, deployment, evaluation, and monitoring.
• Familiarity with ML or data science models and AI-enabled analytics, including LLM, RAG, AI agents, or model tuning and fine-tuning workflows.
• Experience with system design, data architecture, integration, version control, CICD, testing, deployment, and production support.
• Experience with BI tools such as Tableau or Power BI for reporting, data visualization, EDA, and data analysis.
• Knowledge of metadata management, lineage tracking, data-quality frameworks, anomaly detection, testing, and monitoring practices.
• Familiarity with workflow orchestration tools such as Airflow (plus).
• Familiarity with networking, telecommunications, capacity management, or network deployment (preferred).
• Strong analytical and problem-solving skills, including debugging complex data issues and performance bottlenecks.
• Demonstrated ownership across design, development, testing, deployment, documentation, and ongoing support.
• Ability to learn new technologies quickly and communicate effectively across technical and business teams.
• Education: Bachelor’s Degree (degree possession is preferred; alternatives may be considered based on coursework and experience).
• Visa: This position is ineligible for visa sponsorship; must be legally authorized to work in the United States without sponsorship now or in the future.

Technologies

• SQL, Python, AWS, Databricks, Spark
• ELT, ETL
• Machine learning, AI models
• LLM, RAG, AI agents
• Tableau, Power BI
• Metadata management, lineage tracking
• Airflow, CICD

Job Summary

• Support network capacity planning and optimization for next-generation products, including EOHFC, EPON vBNG, and FDX.
• Build and maintain scalable data pipelines, BI and Planning applications, and automated quality check processes to enable forecasting, analysis, and operational decision-making.
• Work across data engineering, analytics, and applied AI, with opportunities to support machine learning models, AI-assisted analysis, and workflow automation.

Location

• Philadelphia, PA (onsite)

Pay Range

• USD 108,578 - 162,868 per year
• Pay range also listed for New Jersey: $108,578.72 - $162,868.08 (base pay within range depends on job-related, non-discriminatory factors such as experience).

Benefits

• Best-in-class Benefits to eligible employees
• Array of options, expert guidance, and always-on tools
• Personalized support physically, financially, and emotionally

Application Window

• 30 days from the date the job is posted, unless the applicant volume requires earlier closure.

Disclaimer: This information describes the general nature and level of work performed and is not a comprehensive inventory of all duties, responsibilities, and qualifications.