> Markdown version of [/jobs/ext/4735645-data-scientist](https://www.wearedevelopers.com/jobs/ext/4735645-data-scientist). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Data Scientist - **Company:** FOOTBRIDGE, INC. - **Location:** Woburn, MA, United States - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Automation of Tests, Cloud Computing, Encodings, Databases, Continuous Integration, Data Transformation, Elasticsearch, Information Retrieval, Python (Programming Language), Natural Language Processing, Named Entity Recognition, Scrum Methodology, Search Technologies, Apache Solr, SQL Databases, Systems Integration, Pinecone, Qdrant, Large Language Models, Generative AI, Indexer, Web Content, Agentic-AI, Kubernetes, Weaviate, Milvus, Data Management, Api Design, Model Context Protocol, Data Pipelines, OpenSearch - **Published:** November 15, 2026 - **Apply:** https://www.careerboard.com/us/en/find-jobs-in-United-States/-BBE8D69F34733C5918/ ## About the Role * Search & Vector Tech: 2+ years of experience with vector indexing, semantic search, and platforms such as Qdrant, Milvus, Weaviate, Pinecone, Apache Solr, Elasticsearch, or OpenSearch. * AI & NLP: 2+ years of hands-on experience with natural language processing, entity extraction/resolution, document chunking, and embedding generation. * Development: 2+ years of experience building MCP servers, integrating LLMs, and programming in Python and SQL. * Engineering: Proven capability in API development, data transformation, and integrating master data into search pipelines. * Clearance: U.S. Citizenship with an active Secret security clearance (or ability to obtain one)., * Experience implementing security access controls and preserving source permissions in search pipelines. * Familiarity with hybrid keyword/vector search systems, reranking models, and Retrieval-Augmented Generation (RAG). * Exposure to containerization, CI/CD pipelines, automated testing, Kubernetes, or cloud infrastructure., * Search & Vector Tech: 2+ years of experience with vector indexing, semantic search, and platforms such as Qdrant, Milvus, Weaviate, Pinecone, Apache Solr, Elasticsearch, or OpenSearch. * AI & NLP: 2+ years of hands-on experience with natural language processing, entity extraction/resolution, document chunking, and embedding generation. * Development: 2+ years of experience building MCP servers, integrating LLMs, and programming in Python and SQL. * Engineering: Proven capability in API development, data transformation, and integrating master data into search pipelines. * Clearance: U.S. Citizenship with an active Secret security clearance (or ability to obtain one). Preferred Skills * Experience implementing security access controls and preserving source permissions in search pipelines. * Familiarity with hybrid keyword/vector search systems, reranking models, and Retrieval-Augmented Generation (RAG). * Exposure to containerization, CI/CD pipelines, automated testing, Kubernetes, or cloud infrastructure. Security Clearance * Level: Secret Travel or Schedule * Full-time schedule.; Embedded within a collaborative engineering scrum team. ## Description * Construct data pipelines using document chunking, embedding generation, and vector retrieval mechanisms. * Build Model Context Protocol (MCP) servers, tools, and workflows to connect search platforms with LLMs and AI agents. * Benchmark, tune, and evaluate domain-specific embedding and reranking models. * Maintain and enhance search functionality across enterprise datasets, web content, and structured databases.