Data Scientist - Startup

About The Company

We are developing a context-aware architecture for enterprise AI that maps organizational decision-making processes by analyzing operational data. The system relies on a dynamic Context Graph to represent business intelligence. This role focuses on researching, developing, and deploying the machine learning models and algorithms that enable next-generation AI agents to navigate and utilize this intelligence.

Technical Responsibilities

• Design and implement machine learning models to extract semantic signals from structured and unstructured enterprise data sources.
• Apply unsupervised learning methods, including hierarchical clustering, pattern mining, and graph-based algorithms, to identify business context at scale.
• Build NLP and embedding-based workflows to integrate unstructured data—such as documentation, metadata, and collaboration logs—into the Context Graph.
• Establish frameworks for model validation, scoring, and statistical drift detection to maintain accuracy as data patterns evolve.
• Engineer production-ready models within an agentic, multi-step reasoning architecture in collaboration with the backend team.
• Evaluate and integrate relevant research in semantic AI, agentic systems, and LLM optimization into the core product.
  
  

• 5+ years of experience in data science, with a proven track record of deploying models in production environments.
• Deep technical foundation in unsupervised learning, specifically clustering and graph algorithms.
• Practical experience with NLP pipelines, including embeddings, semantic similarity, and entity extraction.
• Hands-on experience with Large Language Models (LLMs), RAG architectures, and grounding techniques.
• Familiarity with agentic AI design, including tool use, multi-step reasoning, and context window management.
• Advanced proficiency in Python and the standard ML/Data Science ecosystem.
• Strong SQL skills and experience handling complex query patterns in large datasets.
  
  

• Experience with knowledge graphs or formal ontology modeling.
• Familiarity with enterprise infrastructure, including data warehouses and semantic layers.
• Background in temporal modeling or drift detection.
• Experience evaluating AI agents in a business or enterprise context.