4356 Data Scientist

4356 Data Scientist4356 | SecretJob Description:OVERVIEW:As the Data Scientist, you will report to the onsite Project Team leader and work closely with a small exercise support team. You will own problems end-to-end, to include designing evaluation frameworks, improving prompts and retrieval pipelines, analyzing interview data, and shippingmeasurable improvements into production.GENERAL DUTIES:LLM Quality & EvaluationImprove prompting strategies and structured outputs across reporting formatsincluding law enforcement, intelligence, after-action, interview summaries, andsurvey analysisDesign evaluation sets, scoring rubrics, and automated evaluation pipelines(including LLM-as-judge approaches) for relevance, coherence, completeness,and error modesReduce hallucinations and improve traceability and attributionRAG & Knowledge PipelinesBuild and iterate on RAG pipelines, curated knowledge packs, and question-treetriggersCreate and maintain base datasets (follow-up triggers, Essential Elements ofInformation/Critical Information Requirements, glossaries, watchlist cues) withversioning and documentationTune retrieval and reranking to perform reliably under edge constraints (limitedcompute, memory, and connectivity)Interview AnalyticsAnalyze transcripts to surface evasiveness, inconsistencies, and actionable leadsDevelop labeling strategies, analytic rubrics, and ground-truth datasetsConduct quantitative and qualitative analysis of interview data to identify patternsand support operational decisionsMeasurement & DocumentationBuild lightweight dashboards and metrics for model performance and fieldreliabilityDocument methods and maintain audit trails so outputs remain defensible forgovernment end usersPartner with engineering to validate and ship improvements into productionREQUIRED QUALIFICATIONS:2-5 years of applied data science or NLP experienceStrong Python skills (pandas, NumPy, scikit-learn) with comfort standing upexperiments and pipelinesHands-on experience with LLMs: prompt engineering, output evaluation, safety,and quality controlsExperience with unstructured text data - cleaning, labeling, building evaluationmetricsProficiency in data analysis, reporting, and visualization for technical and non-technical audiencesAbility to work on-site in the El Paso / Las Cruces / WSMR areaDESIRED QUALIFICATIONS:RAG implementation experience (vector databases, embeddings, reranking)Experience with structured evaluation frameworks (RAGAS, custom LLM-as-judge, or equivalent)Familiarity with edge or offline deployment constraintsExposure to interview analytics, structured debriefing, structured reporting, orHUMINT-adjacent workflowsExperience delivering in classified or regulated environmentsCLEARANCE:Active Secret clearanceJob DetailsCity : El PasoState : TX