Data Scientist

Data Scientist (Elasticsearch-Focused) —

Position Overview
We’re seeking a Senior Data Scientist / Data Team Lead to design, build, and deploy data science solutions powered by Elasticsearch for mission-focused analytic workflows. This role delivers end-to-end pipelines—from data ingestion and model development to production APIs and user-facing search experiences—supporting complex text, image, and video datasets. The ideal candidate blends strong DS fundamentals (NLP/ML/CV), production engineering habits (Docker/Linux/APIs), and hands-on experience building Elasticsearch-backed search and retrieval capabilities at scale.
Eligibility Requirement: Candidate must hold an active TS/SCI clearance.

What You’ll Do
Elasticsearch Search, Retrieval & Analytics (Primary)

Build and maintain Elasticsearch-backed search solutions that enable fast retrieval across large, shared repositories and mission datasets.
Implement pipelines that transform raw data into searchable content stores, supporting discovery across documents, structured data, and media (image/video/text).
Design and deliver search workflows including indexing, query experience, and access controls to support controlled data environments.
Integrate Elasticsearch with downstream analytics, dashboards, and applications to accelerate analyst productivity and decision-making.

Applied Data Science (NLP + CV)

Develop and deploy NLP pipelines for translation, topic modeling, sentiment, entity-focused analysis, and narrative monitoring.
Deliver computer vision capabilities such as detection/tracking, classification, segmentation, facial/attribute recognition, OCR, and re-identification—optimized for operational use.
Establish evaluation methods (precision/recall/F1) and optimize thresholds to reduce analyst review burden and improve triage.

Production Delivery & Engineering Enablement

Productionize models and analytics via APIs and services (e.g., FastAPI) and ship containerized solutions using Docker in Linux environments.
Build ingestion → preprocessing → inference → storage pipelines, with basic monitoring/alerting and deployment runbooks.
Collaborate with engineers to harden services, improve reliability, and ensure solutions meet compliance and release expectations.

Technical Leadership & Execution (Lead-Level Expectations)

Own delivery from project charter and requirements through deployment, including scope, roadmaps, stakeholder communications, and executive readouts.
Mentor junior data scientists, set coding/documentation standards, and enforce reproducible training and evaluation workflows.
Define success metrics (KPIs/OKRs) and drive continuous improvement in quality, throughput, and mission impact.


Required Qualifications

Active Top Secret Clearance
Strong hands-on experience as a Data Scientist delivering production solutions (not just research).
Demonstrated experience building Elasticsearch-backed search/retrieval capabilities, including indexing/search workflows and integrating search into applications.
Advanced proficiency in Python and working knowledge of SQL.
Experience with ML frameworks (e.g., PyTorch, TensorFlow, scikit-learn) and shipping models into production.
Solid experience in Linux environments (Ubuntu/WSL2) and containerization with Docker.
Experience integrating systems via APIs and version control (Git).


Preferred Qualifications (Nice to Have)

CV toolchains: OpenCV, YOLO/YOLOv8, DLIB, detection/tracking, segmentation, OCR, re-ID.
NLP/LLM experience: Transformers (BERT/RoBERTa), multilingual pipelines, RAG, LangChain/vector DB workflows.
Data platforms: Spark/pySpark, Databricks; exposure to AWS/Azure.
Visualization and reporting: Tableau, Power BI; ability to brief technical/non-technical stakeholders.
Experience leading teams/programs: backlog ownership, sprint ceremonies, requirements/acceptance criteria, and delivery governance.