Hands-on senior technical resource on a two-person KCS project team focused on developing an ML solution for identifying high-value Cisco Learning engagement opportunities.

Required Skills

Machine Learning / Statistics

• Traditional predictive ML
• Statistical modeling
• Classification / probability-based modeling
• Feature engineering and feature selection
• Feature importance / ablation analysis
• Model evaluation and calibration
• Class-imbalance techniques
• Holdout and temporal validation
• Leakage identification and prevention
• Logistic Regression
• Gradient Boosted Trees, including XGBoost/LightGBM
• Scikit-learn or comparable ML framework

Traditional ML, feature engineering, statistical modeling, classification/probability analysis, class imbalance, and seasonality as key areas of need. 

Languages / Data

•  Advanced Python
• SQL
• Pandas
• NumPy
• Relational/database analysis
• Structured + unstructured data

ML Lifecycle

• ML training/evaluation workflows
• Feature-engineering pipelines
• Model monitoring
• Model registries/versioning
• Experiment tracking
• Automated testing/retraining concepts
• Production-oriented ML practices

The operating model states that Kforce work will include understanding existing signals, building experiments against individual data sources, determining associated features/dimensions, and designing/proposing feature-engineering ML stages. Deep ML expertise is mandatory. 

Preferred Skills

•  Sales-domain feature engineering / predictive analytics
• Propensity modeling / opportunity or lead scoring
• Revenue-oriented predictive analytics
• Customer adoption, consumption, or renewal modeling
• Survival / time-to-event analysis
• NLP / text analytics
• MLflow
• Feature Store concepts
• Cloud ML ecosystem exposure
• Enterprise data and governance
• Prior Cisco experience