Job Title: Senior Data Scientist – GenAI & Knowledge Graphs Location: Remote Department: AI & Data Science Employment Type: Full-time for all Visa and H1B for Contract Job Summary We are looking for a Senior Data Scientist with hands-on expertise in building Generative AI applications using Knowledge Graphs, Graph Databases, and multi-agent systems. The ideal candidate will have strong experience in LLM-driven development, agentic AI workflows, and semantic data modeling using OWL and RDF. Key Responsibilities • Build and maintain graph-based data pipelines using technologies like Neo4j, Amazon Neptune, or Stardog. • Design and implement knowledge graphs and ontologies using OWL, Protégé, TopBraid, or similar tools. • Integrate knowledge graphs with GenAI pipelines, improving context grounding and retrieval for LLM-based applications. • Develop and orchestrate multi-agent systems using LangGraph, CrewAI, or AutoGen, including agent-to-agent (A2A) communication, memory modules, and reasoning chains. • Leverage MCP servers and agent runtime engines to deploy agent-based GenAI applications for real-world scenarios such as customer support, content synthesis, and document analysis. • Work on RAG architectures involving embedding models, vector stores (e.g., FAISS, Pinecone), and structured semantic layers. • Collaborate with engineers and junior data scientists on project delivery and model deployment. • Write clean, reusable code in Python using ML/LLM frameworks such as LangChain, HuggingFace, and OpenAI SDKs. Required Skills & Experience • 5–8 years of experience in data science, with 2+ years in LLM/GenAI development. • Hands-on experience with GraphDBs (Neo4j, Neptune, TigerGraph) and SPARQL or Cypher. • Proficiency in ontology modeling using OWL/RDF and familiarity with semantic reasoning tools. • Strong experience in building agentic AI applications, including use of LangGraph, AutoGen, or CrewAI. • Understanding of multi-agent communication protocols (A2A), agent memory, and orchestration layers. • Solid understanding of data wrangling, NLP, and embedding models (sentencetransformers, OpenAI embeddings, etc.). • Python proficiency and experience with REST APIs, data processing libraries (pandas, NumPy), and JSON-LD. Preferred Qualifications • Master’s degree in Data Science, Computer Science, AI/ML, or a related field. • Knowledge of cloud-native deployment is a plus (though not mandatory). • Open-source contributions, blog posts, or internal project showcases in the GenAI/Knowledge Graph space.