> Markdown version of [/jobs/ext/4790560-professional-data-scientist-iii](https://www.wearedevelopers.com/jobs/ext/4790560-professional-data-scientist-iii). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Professional - Data Scientist III - **Company:** Everforth Apex - **Location:** Hendersonville, NC, United States (Remote available) - **Salary:** $145,600 - $166,400 - **Contract:** Permanent contract - **Skills:** Python (Programming Language), Operational Databases, SciPy, SQL Databases, Supervised Learning, Data Processing, Feature Engineering, Large Language Models, SHAP (Shapley Additive Explanations), Apache Spark, Information Technology, Xgboost, Machine Learning Operations, Databricks, Data Generation - **Published:** November 19, 2026 - **Apply:** https://www.dice.com/job-detail/a71533de-d8d1-4030-9008-e270b27a0bfe ## About the Role Education: A bachelor degree in Data Science, Computer Science, Statistics, or a related quantitative field is preferred. Experience: Demonstrated experience in government or defense contracting environments is required. Candidates must possess practical experience in modeling and feature engineering on tabular and time-series data. Technical Skills: Proficiency with Databricks, Python, SQL, and Spark is required. Expertise must include supervised learning on tabular data using gradient boosting and regularized regression, alongside model calibration under class imbalance. Experience with anomaly detection techniques, optimization methods utilizing tools such as OR-Tools, Pyomo, or SciPy, and model explainability using SHAP is necessary. Candidates must understand privacy-preserving synthetic data generation from restricted source data, including re-identification risk management. Preferred Qualifications * Experience modeling investigative, vetting, fraud, or insider-threat data. * Direct experience with federal security standards, NIST guidelines, or controlled unclassified information handling. * Familiarity with LLM and generative AI workflows to support collaborative document intelligence workstreams. * Experience with H2O platforms, Unity Catalog, and Databricks Asset Bundles. * Experience performing fairness and adverse-impact analyses in regulated decision-support settings. ## Description * Develop risk-scoring models over synthetic tabular data by engineering features from curated medallion-layer tables. * Build anomaly and outlier detection systems to identify irregularities in records and process data. * Design optimization models for prioritization, routing, and resource allocation. * Validate model performance thoroughly, focusing on calibration, discrimination, stability, and explainability. * Package deliverables as jobs and asset bundles tracked in MLflow. * Document assumptions, limitations, and requirements for post-authorization validation against production data. * Collaborate across technical and non-technical teams to facilitate knowledge transfer.