Stephen Minemann
Analytics Engineer
Snowflake + SQL · Python/pandas · Data Modeling · Operational Metrics
customer records analyzed → high-probability plan-migration candidates identified
Cost-Per-Site reduction across 6,000+ cell sites · $180 → $150
repeatable Nokia outage analytics dataset for T-Mobile's Radio Replacement program · productized into a reusable Snowflake aggregation
about.
Most data engineers have never touched the infrastructure they're querying. I have. Ten years at T-Mobile, starting in retail, moving through Network Operations, an SRE internship, and now as an Associate Systems Architect Engineer, gave me something most analytics work is missing: firsthand knowledge of how the systems actually behave before the data reaches a table.
That grounding shapes how I build. When I'm writing a Snowflake SQL model or transforming alarm extracts in pandas, I already know what an edge case looks like in the field. I built T-Mobile's first repeatable outage analytics dataset for the Nokia Radio Replacement program because no method existed to connect project schedules with national alarm data. I knew exactly what the raw signals meant. I defined the downtime logic, parameterized it by site, market, and time window, and productized it into a reusable aggregation table once cross-market demand grew. The same pattern repeated across a CPS financial model for 6,000+ cell sites, a compliance reconciliation workflow across three Snowflake sources, and a plan-migration candidate dataset surfaced from 90M customer records.
The thread is always the same: turning messy operational questions into trusted, reusable datasets and self-service analytics products. That's Analytics Engineering, and that's where I'm headed. I'm also a strong fit for Data Engineering and Business Analytics roles where operational domain depth matters.
featured analytics products.
// work built at T-Mobile
Nokia Radio Replacement Outage Analytics
internalBuilt the first repeatable outage-time dataset for the Nokia Radio Replacement program after a director-backed PMO request revealed no method existed to connect project schedules with national alarm data. Translated Nokia schedules, site lists, and maintenance windows into Snowflake SQL parameters to isolate qualifying alarms by site, project, market, and time window. Defined downtime logic and transformed raw alarm extracts in pandas into filterable CSV/Power BI outputs distributed through SharePoint for PM validation and leadership review. Productized into a reusable Snowflake aggregation table once cross-market demand grew.
// internal project · code and values have been sanitized and made ambiguous
ML Site / Premise Matching Data Product
internalMatching features combining normalized address tokens, geospatial distance, fuzzy similarity, and candidate ranking to link cell-site inventory to premise IDs. Designed a validation and exception-tracking schema for match status, review outcomes, metadata gaps, and audit history.
// internal project · code and values have been sanitized and made ambiguous
Enterprise Data Integrity & Compliance Dataset
internalRepeatable cleanup workflow for site-compliance data: reconciled 3,425 missing-site records and 7,046 MWR compliance rows across Snowflake source exports, field assignment files, and site metadata. Standardized raw compliance values into pass/fail/remediation buckets and generated owner-ready exception queues. Identified 1,013 one-field correction candidates packaged as correction-ready outputs.
// internal project · code and values have been sanitized and made ambiguous
Cell Site Battery Monitoring Tool
publicProduction-grade Python CLI that reads CSV/XLSX site lists, authenticates to power-cabinet web interfaces, collects battery state-of-charge and remaining runtime, and exports outage triage reports sorted lowest battery to highest. Env-based credentials, timeout controls, HTTPS to HTTP fallback, masked IP logging, debug snapshots, and timestamped outputs. Built to run safely during disaster recovery.
Cost Per Site Performance Data Model
internalSite-level Cost-Per-Site model for tower crew support and material spend across 6,000+ cell sites. This gave leadership a repeatable metric instead of one-off cost pulls. Normalized expense categories, surfaced outlier sites, trend views, and priority filters. Helped reduce average CPS from ~$180 to ~$150, beating the $160 target.
// internal project · code and values have been sanitized and made ambiguous
skills.
Analytics Engineering
- Data Modeling
- Metric Definitions
- ELT / ETL
- CTEs & Window Functions
- Data Marts
- Reusable Aggregation Tables
- Self-Service Datasets
- Reconciliation & Validation
Data Platforms & SQL
- Snowflake
- SQL
- Power BI
- PostgreSQL
- SQL Server
- Alteryx
- SharePoint
- dbt exposure
- Airflow exposure
Python & Tooling
- Python
- pandas
- NumPy
- Jupyter
- scikit-learn
- REST APIs
- Postman
- Git / GitHub / GitLab
- JSON / XML / YAML
experience.
Associate Systems Architect Engineer
T-Mobile- Build Snowflake SQL and Python workflows across enterprise customer and network datasets; define source logic, metric rules, QA checks, and reusable outputs that inform operational strategy and long-term investment decisions.
- Analyzed ~90M customer records and narrowed targeting to ~4M high-probability plan-migration candidates using behavioral and usage segmentation, balancing ARPU upside with churn and customer-experience considerations.
- Partnered with a Senior Data Scientist on an FCC speed-forecasting prototype; profiled site-performance data for completeness, temporal coverage, sampling constraints, and model readiness before recommending next-step data improvements.
- Use ChatGPT, Claude, and Cursor to accelerate SQL/Python scaffolding, refactoring, debugging, and documentation. I independently validate all outputs against real data and source-system behavior.
Network Operations Engineer
T-Mobile- Built Python and SQL telemetry analytics and metadata validation workflows across 6,000+ cell sites to expose recurring degradation patterns, missing data, compliance gaps, cost variance, and reliability risks.
- Designed the Cost-Per-Site data model and reporting workflow for crew and material spend; reduced average CPS from ~$180 to ~$150, beating the $160 target and giving leaders site-level outlier visibility.
- Owned Tier II incident analytics, translating recurring alarms into detection logic, exception categories, mitigation playbooks, and preventive remediation while supporting 99.90%+ availability.
- Built a Python battery-monitoring extract that ingested site lists, queried power-cabinet web interfaces, parsed battery/runtime data, and produced outage-priority outputs sorted by lowest remaining backup power (now open-sourced as cheddaburger/power_cabinet_tool).
System Reliability Engineer Intern
T-Mobile- Collaborated with SRE and DevOps engineers on Docker, Kubernetes, Splunk, Grafana, microservices troubleshooting, observability, and command-line debugging of containers and services.
- Built hands-on frontend work in a stretch assignment using JavaScript, Node.js, Vue, Webpack, and HTML/CSS and picked up the modern frontend toolchain end-to-end.
- Used GitHub and GitLab for collaborative version control and CI workflows in production-style engineering assignments.
Mobile Expert / Signature Mobile Expert
T-MobileThe start of the arc.
- Ranked #1 in sales performance and maintained 90%+ NPS across a 6-year tenure.
- Led device and service troubleshooting; trained peers on legacy Sprint systems during the post-merger transition.
- Documented repeatable customer-resolution workflows that scaled across the store team.
education & learning.
B.S. Computer Science
Colorado Technical University
Snowflake "Zero to Agents" Workshop
AWS Certified Machine Learning – Specialty
Amazon Web Services
dbt Analytics Engineering Certification
dbt Labs
contact.
Let's build something worth measuring.
Bloomington, MN · Open to remote, hybrid, or on-site
bilingual? try typing es