Data Scientist

This is a fully remote position, open to applicants in Maryland.

📋 Description

• Create analytical and machine-learning methodologies that support permitting and natural resource applications.

• Construct and uphold labeled datasets, evaluation corpora, and benchmark datasets for AI-driven services.

• Establish quantitative evaluation methods for classification, extraction, retrieval, summarization, entity matching, and other AI/NLP functionalities.

• Assess LLM and agentic workflows, focusing on output quality, retrieval efficacy, task completion, failure modes, and reliability.

• Examine public-comment datasets and create reusable features and evaluation datasets for comment-processing applications.

• Utilize NLP and machine learning techniques on both structured and unstructured data.

• Assess embedding models, semantic retrieval methods, document-ranking strategies, and AI-generated results.

• Formulate statistical methods for identifying anomalies, reconciliation problems, missing data, and inconsistent records.

• Collaborate with Content Pipeline Engineers to evaluate OCR, extraction, and document-retrieval performance.

• Work with Data Engineers to guarantee that analytical datasets and evaluation pipelines are reproducible and production-ready.

• Assist in entity matching and harmonization among data sourced from various systems.

• Design experiments and validation methodologies with clearly defined success metrics.

• Contribute to certified analytical data products, metrics, and governed datasets.

• Develop reproducible Python analyses, models, evaluation pipelines, and technical documentation.

• Convey model performance, limitations, uncertainty, and failure modes to both technical and non-technical audiences.

⛳️ Requirements

• Bachelor's degree in Data Science, Statistics, Computer Science, Mathematics, Engineering, or a related quantitative field.

• Over 5 years of pertinent experience in data science, applied machine learning, or quantitative analytics.

• Proficient in Python and SQL.

• Experience with statistical analysis, machine learning, NLP, and unstructured text data.

• Proven background in designing labeled datasets, benchmark datasets, and train/test evaluation frameworks.

• Experience assessing LLM, RAG, or agentic AI solutions, focusing on retrieval quality, output accuracy, and failure modes.

• Strong grasp of model-evaluation techniques, including precision, recall, F1 score, ranking metrics, confusion matrices, and related assessments.

• Familiarity with embeddings, semantic retrieval, or vector-based search.

• Capability to develop reproducible analytical and evaluation workflows.

• Ability to differentiate data-quality issues from model-performance challenges.

• Excellent communication skills for articulating analytical outcomes, limitations, and uncertainties.

• Bonus: Experience with agent evaluation frameworks or LLM observability tools.

• Bonus: Familiarity with agentic frameworks like LangChain, LangGraph, or similar orchestration systems.

• Bonus: Experience with OpenSearch, vector databases, or enterprise search platforms.

• Bonus: Knowledge of document AI or OCR pipelines.

• Bonus: Experience in geospatial analysis.

• Bonus: Background in developing entity-resolution, record-linkage, or data-quality models.

• Bonus: Experience in the U.S. Federal Government sector.

• Bonus: Understanding of permitting, regulatory, environmental, energy, or natural-resource datasets.

🏝️ Benefits

• Medical coverage

• Dental coverage

• Vision coverage

• 401k plan with employer contribution

• Paid holidays

• Vacation

• Tuition reimbursement