Senior Data Scientist – AI‑driven Patent Analytics

About the role

We are looking for a Senior Data Scientist to shape the next‑generation AI assistant, Protégé, within our PatentSight platform. You will define and validate agentic AI capabilities that streamline complex intellectual‑property workflows, turning large‑scale patent data into actionable insights.

Key responsibilities

• Design and implement NLP, LLM, and generative‑AI approaches such as Retrieval‑Augmented Generation and advanced prompting.
• Define multi‑step, agentic workflows for IP tasks and create reasoning strategies.
• Develop hybrid search solutions that combine semantic and lexical techniques, and establish evaluation metrics.
• Analyse massive IP datasets to extract insights, improve model performance, and benchmark results.
• Translate experimental findings into clear product recommendations and measurable business impact.
• Collaborate closely with product managers, IP experts, and engineering teams to align solutions with user needs.

Required profile

• Degree in a quantitative or technical discipline (e.g., Statistics, Computer Science, Mathematics, Data Science).
• Strong experience in machine learning, natural language processing, and LLM‑based modeling.
• Proven track record designing and running experiments, including model evaluation and iteration.
• Advanced Python programming skills.

Required skills

• Python
• Machine Learning
• Natural Language Processing (NLP)
• Large Language Models (LLMs)
• Generative AI (prompt engineering, RAG)
• Hybrid search (semantic + lexical), embeddings, vector databases
• Agent frameworks (Google ADK, LangChain, LangGraph, AutoGen)
• Data analysis tools