Data Scientist III – AI-driven Patent Analytics

About the role

We are looking for a Data Scientist III to design and validate AI‑driven product capabilities for Protégé, our next‑generation agentic AI assistant in PatentSight. You will shape the roadmap for machine‑learning, natural‑language processing and large‑language‑model solutions that automate complex intellectual‑property workflows, turning massive patent data into actionable insights.

Key responsibilities

• Develop and implement NLP, LLM and generative‑AI approaches, including retrieval‑augmented generation and prompt strategies for patent search.
• Define multi‑step agentic workflows and reasoning strategies for IP tasks.
• Design hybrid retrieval systems that combine semantic and lexical search, and create evaluation metrics such as relevance and ranking quality.
• Analyse large‑scale IP datasets to extract insights and improve model performance.
• Establish best practices for model evaluation, validation and benchmarking.
• Translate experimental results into clear product recommendations and measurable business impact.
• Collaborate with product managers, IP experts and engineering teams to align solutions with user needs.

Required profile

• Degree in a quantitative or technical field (e.g., Statistics, Computer Science, Mathematics, Data Science).
• Strong experience in machine learning, NLP and LLM‑based modeling.
• Proven track record designing and running experiments, including model evaluation and iteration.
• Proficient coding skills in Python.

Required skills

• Python programming
• Natural Language Processing (NLP)
• Large Language Models (LLM)
• Generative AI techniques (prompt engineering, RAG)
• Hybrid search (semantic + lexical) using embeddings and vector databases
• Agent frameworks (Google ADK, LangChain, LangGraph, AutoGen)
• Data analysis tools
• Statistical modeling