<h2>Overview</h2> <p>We are seeking a <strong>Data Scientist</strong> to support applied machine learning, natural language processing, AI evaluation, data quality, and analytical product development for a federal permitting modernization initiative.</p> <p>The Data Scientist will work across structured and unstructured data, including public comments, permitting records, compliance information, documents, and geospatially linked datasets. A key focus of the role will be developing representative evaluation datasets and quantitative methods to measure the performance, reliability, and limitations of AI-enabled and agentic solutions.</p> <p>This position is remote.</p> <p><strong>Duties & Responsibilities</strong></p> <ul> <li>Develop analytical and machine-learning approaches supporting permitting and natural-resource use cases.</li> <li>Build and maintain labeled datasets, evaluation corpora, and benchmark datasets for AI-enabled services.</li> <li>Define quantitative evaluation methodologies for classification, extraction, retrieval, summarization, entity matching, and other AI/NLP capabilities.</li> <li>Evaluate <strong>LLM and agentic workflows</strong>, including output quality, retrieval performance, task completion, failure modes, and reliability.</li> <li>Analyze public-comment datasets and develop reusable features and evaluation datasets for comment-processing services.</li> <li>Apply NLP and machine-learning techniques to structured and unstructured data.</li> <li>Evaluate embedding models, semantic retrieval strategies, document-ranking techniques, and AI-generated outputs.</li> <li>Develop statistical approaches for detecting anomalies, reconciliation issues, missing data, and inconsistent records.</li> <li>Partner with Content Pipeline Engineers to measure OCR, extraction, and document-retrieval performance.</li> <li>Partner with Data Engineers to ensure analytical datasets and evaluation pipelines are reproducible and production-ready.</li> <li>Support entity matching and harmonization across data originating in multiple source systems.</li> <li>Design experiments and validation approaches with clearly defined success metrics.</li> <li>Contribute to certified analytical data products, metrics, and governed datasets.</li> <li>Develop reproducible Python analyses, models, evaluation pipelines, and technical documentation.</li> <li>Communicate model performance, limitations, uncertainty, and failure modes to technical and non-technical stakeholders.</li> </ul> <p><strong>Educational Requirements</strong></p> <ul> <li>Bachelor's degree in Data Science, Statistics, Computer Science, Mathematics, Engineering, or a related quantitative discipline.</li> </ul> <p><strong>Requirements</strong></p> <ul> <li><strong>5+ years</strong> of relevant data science, applied machine learning, or quantitative analytics experience.</li> <li>Strong Python and SQL skills.</li> <li>Experience with statistical analysis, machine learning, NLP, and unstructured text data.</li> <li>Experience designing labeled datasets, benchmark datasets, and train/test evaluation frameworks.</li> <li>Experience evaluating <strong>LLM, RAG, or agentic AI solutions</strong>, including retrieval quality, output accuracy, and failure modes.</li> <li>Strong understanding of model-evaluation techniques, including precision, recall, F1, ranking metrics, confusion matrices, and related measures.</li> <li>Experience with embeddings, semantic retrieval, or vector-based search.</li> <li>Experience developing reproducible analytical and evaluation workflows.</li> <li>Ability to distinguish data-quality issues from model-performance issues.</li> <li>Strong ability to communicate analytical results, limitations, and uncertainty.</li> </ul> <p><strong>Bonus Skills</strong></p> <ul> <li>Experience with agent evaluation frameworks or LLM observability tools.</li> <li>Experience with <strong>agentic frameworks such as LangChain, LangGraph, or similar orchestration frameworks</strong>.</li> <li>Experience with OpenSearch, vector databases, or enterprise search platforms.</li> <li>Experience with document AI or OCR pipelines.</li> <li>Experience with geospatial analysis.</li> <li>Experience developing entity-resolution, record-linkage, or data-quality models.</li> <li>Experience working in the <strong>U.S. Federal Government space</strong>.</li> <li>Experience with permitting, regulatory, environmental, energy, or natural-resource datasets.</li> </ul> <h2>Benefits and Salary</h2> <p>We attract the best people in the business with our competitive benefits package that includes medical, dental and vision coverage, 401k plan with employer contribution, paid holidays, vacation, and tuition reimbursement.</p> <p>If you enjoy being a part of a high performing, professional service and technology focused organization, please apply today!</p>