Junior Biostatistician

Responsibilities Acquire, integrate, and prepare data from multiple sources to enable operational reporting, readiness analytics, and decision support. Design and implement ETL/ELT pipelines using SQL Server and Databricks leveraging Apache Spark (PySpark) for scalable batch processing and data transformation. Develop and maintain curated, analysis-ready datasets (e.g., dimensional models, governed reporting tables) with attention to data quality, lineage, and repeatability. Optimize data processing performance (partitioning strategies, efficient joins, job tuning) and contribute to reliable scheduling/orchestration and monitoring of recurring workloads. Apply statistical methods, data mining, and machine learning to generate actionable insights, forecasts, and predictive analytics relevant to military missions and readiness. Create dashboards and analytical products using Power BI, including semantic modeling and measures to support consistent metrics and reporting. Support low-code solutions by integrating data products into Power Apps (Canvas and Model-Driven) and automations using Power Automate. Contribute to text and language-focused use cases by preparing and analyzing unstructured data (basic NLP preprocessing, labeling/curation, feature creation). Demonstrate familiarity with LLMs and agent concepts (prompting patterns, retrieval‑style workflows, evaluation considerations) and assist senior team members in implementing these capabilities where appropriate. Document data sources, transformations, assumptions, and analytical methodologies to ensure transparency and operational continuity. Requirements Bachelor’s degree with one to two (1‑2) years’ experience in quantitative science, social science or related discipline. Proficient with the suite of Microsoft Office programs, including Word, Excel and Access. Working knowledge of SQL Server (SQL/T‑SQL), including querying, joins, indexing basics, and working with relational schemas. Hands‑on experience or strong exposure to Databricks and Apache Spark (preferably PySpark) or comparable systems for scalable data preparation. Foundational programming skills in Python or R for analysis, data manipulation, and ML workflows. Possess an understanding of data engineering concepts: ETL/ELT, data modeling basics, data quality checks, reproducible pipelines, and version control (Git). Experience building visual analytics with Power BI (reports, datasets/semantic models, DAX fundamentals preferred). Familiarity with the Power Platform: Power Apps (Canvas and Model‑Driven) and Power Automate for workflow integration. Basic familiarity with NLP and Large Language Models, including typical use cases and data requirements (text preparation, evaluation datasets, governance considerations). Ability to communicate clearly with stakeholders and translate mission needs into data requirements and analytical outputs. Experience with web application development technologies: HTML, CSS, JavaScript, React, plus backend exposure to Django or ASP.NET Core. Experience with advanced Spark/Databricks patterns (Delta tables, incremental loads, job/workflow scheduling, performance tuning). Familiarity with deploying analytics/ML into applications (APIs, dashboards, or integrated workflows) and basic MLOps concepts. #J-18808-Ljbffr