Data Scientist III – AI-driven Patent Analytics

About the role

We are seeking a Data Scientist III to design and validate agentic AI‑driven product capabilities within Protégé in PatentSight. The role focuses on defining what to build and why, leveraging machine learning, NLP and large language models to solve complex intellectual‑property workflows, and partnering with engineers to turn validated approaches into scalable, customer‑facing solutions.

Key responsibilities

• Develop and implement NLP, LLM and generative‑AI approaches such as retrieval‑augmented generation and prompt strategies for patent search.
• Define agentic workflows and multi‑step reasoning strategies for IP tasks.
• Design hybrid retrieval methods (semantic + lexical) and evaluation metrics like 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 business impact.
• Collaborate with product, IP experts and engineers 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 designing and running experiments, including model evaluation and iteration.
• Proficiency in Python and statistical modelling.

Required skills

• Machine learning, NLP and large language model development.
• Generative AI techniques such as prompt engineering and RAG.
• Hybrid search using embeddings and vector databases.
• Agent frameworks (Google ADK, LangChain, LangGraph, AutoGen).
• Data analysis tools and large‑scale text processing.

What we offer

• Flexible working hours and hybrid work options.
• Generous holiday allowance with the option to buy additional days.
• Private medical benefits, health screening and eye‑care vouchers.
• Competitive pension scheme and share‑option plan.
• Wellbeing programs, employee assistance and learning & development resources.