Society of Exploration Geophysicists
Data Scientist
Society of Exploration Geophysicists - Seattle, Washington, us, 98127
Work at Society of Exploration Geophysicists
Overview
- View job
Overview
Job Title:
Data Scientist – GenAI & Knowledge Graphs Location:
Seattle, WA, US Employment Type:
Full-time Job Summary We are hiring a Data Scientist to support the development of Generative AI applications that leverage knowledge graphs, GraphDBs, and multi-agent orchestration. This role is hands-on, focused on practical implementation of GenAI patterns using state-of-the-art open-source libraries and graph technologies. Key Responsibilities Develop graph data models using Neo4j, RDF, and SPARQL/Cypher for building semantic knowledge representations. Support the design and enrichment of ontologies using OWL and Protégé, aligning data schemas for GenAI use cases. Build components of agentic AI systems using frameworks like LangGraph, CrewAI, or AutoGen under senior guidance. Assist in implementing RAG pipelines, working with vector databases and embedding models for improved document search. Implement agent-to-agent (A2A) interaction flows and agent memory structures in prototype-level applications. Work with Python, integrating APIs from LLM providers (OpenAI, Anthropic, etc.) with knowledge graph backends. Maintain documentation, test cases, and reusable code modules for internal projects. Required Skills & Experience 2–4 years of experience in data science or NLP/ML roles. Exposure to GraphDBs like Neo4j or Neptune and basic query languages like Cypher or SPARQL. Understanding of ontology basics, OWL standards, and tools like Protégé. Familiarity with GenAI tools and libraries (LangChain, LangGraph, CrewAI, etc.). Strong Python skills with ability to work with REST APIs, LLM SDKs, and embedding models. Good documentation, debugging, and collaboration skills. Preferred Qualifications Bachelor’s degree in Data Science, Computer Science, or related field. Familiarity with agent protocols (MCP, A2A) and experience participating in GenAI POCs or hackathons. Interest in growing expertise in semantic AI, graph-based ML, and agentic systems.
#J-18808-Ljbffr
Data Scientist – GenAI & Knowledge Graphs Location:
Seattle, WA, US Employment Type:
Full-time Job Summary We are hiring a Data Scientist to support the development of Generative AI applications that leverage knowledge graphs, GraphDBs, and multi-agent orchestration. This role is hands-on, focused on practical implementation of GenAI patterns using state-of-the-art open-source libraries and graph technologies. Key Responsibilities Develop graph data models using Neo4j, RDF, and SPARQL/Cypher for building semantic knowledge representations. Support the design and enrichment of ontologies using OWL and Protégé, aligning data schemas for GenAI use cases. Build components of agentic AI systems using frameworks like LangGraph, CrewAI, or AutoGen under senior guidance. Assist in implementing RAG pipelines, working with vector databases and embedding models for improved document search. Implement agent-to-agent (A2A) interaction flows and agent memory structures in prototype-level applications. Work with Python, integrating APIs from LLM providers (OpenAI, Anthropic, etc.) with knowledge graph backends. Maintain documentation, test cases, and reusable code modules for internal projects. Required Skills & Experience 2–4 years of experience in data science or NLP/ML roles. Exposure to GraphDBs like Neo4j or Neptune and basic query languages like Cypher or SPARQL. Understanding of ontology basics, OWL standards, and tools like Protégé. Familiarity with GenAI tools and libraries (LangChain, LangGraph, CrewAI, etc.). Strong Python skills with ability to work with REST APIs, LLM SDKs, and embedding models. Good documentation, debugging, and collaboration skills. Preferred Qualifications Bachelor’s degree in Data Science, Computer Science, or related field. Familiarity with agent protocols (MCP, A2A) and experience participating in GenAI POCs or hackathons. Interest in growing expertise in semantic AI, graph-based ML, and agentic systems.
#J-18808-Ljbffr