Data Scientist III

Overview

In this role you will help design and validate AI-driven capabilities for Protégé in PatentSight, focusing on NLP, LLMs, and retrieval for complex IP workflows. You will work with engineers to translate experimental results into scalable, customer-facing features that empower patent analysis. The role combines modeling, experimentation, and product collaboration to shape decision-ready insights. You contribute to an innovative, collaborative team advancing AI-powered patent intelligence with real-world impact.

Pay / Benefits

• Generous holiday allowance
• Private medical benefits
• Pension scheme
• Life assurance
• Employee assistance program
• Learning and development resources

Responsibilities

• Develop NLP, LLM, and generative AI approaches (e.g., RAG, prompt strategies, patent search)
• Define agentic workflows and multi-step IP task reasoning
• Design and optimize hybrid search strategies (semantic + lexical) and evaluation metrics
• Analyze large-scale IP datasets to improve model performance
• Establish best practices for model evaluation, validation, and benchmarking
• Translate experimental results into product recommendations and business impact
• Collaborate with product, IP experts, and engineers to align solutions with user needs

Key requirements

• Degree in a quantitative or technical field (Statistics, Computer Science, Mathematics, Data Science, etc.)
• Strong experience in machine learning, NLP, and LLM-based modeling
• Experience designing and running experiments with model evaluation and iteration
• Strong Python coding skills
• Experience with generative AI techniques (prompt engineering, RAG)
• Experience designing and evaluating hybrid search using embeddings and vector databases
• Experience designing agentic workflows and applying agent frameworks (e.g., Google ADK, LangChain, LangGraph, AutoGen)
• Proficiency in data analysis tools
• Strong foundation in statistics, modeling, and large-scale text processing

• Collaborative cross-functional communication
• Problem solving in ambiguous domains
• Ability to translate technical results into product decisions
• NLP and LLM modeling
• Generative AI techniques (prompt engineering, RAG)
• Hybrid search design (semantic + lexical) with embeddings/vector databases

…