Data Scientist III

About the role

We are looking for a Data Scientist III to design and validate agentic AI‑driven product capabilities within Protégé in PatentSight. The role focuses on applying machine learning, NLP and large language models to solve complex intellectual property workflows and translate experimental results into scalable, customer‑facing solutions.

Key responsibilities

• Develop and implement NLP, LLM, and generative AI approaches (e.g., RAG, prompt strategies, patent search).
• Define agentic workflows and reasoning strategies for multi‑step IP tasks.
• Develop retrieval strategies, including hybrid search (semantic + lexical), and 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 business impact.
• Collaborate with product, IP experts, and engineers to align solutions with user needs.

Required profile

• Degree in a quantitative or technical field (Statistics, Computer Science, Mathematics, Data Science, etc.).
• Strong experience in machine learning, NLP, and LLM‑based modeling.
• Proven ability to design and run experiments, including model evaluation and iteration.
• Strong coding skills in Python.
• Experience with generative AI techniques such as prompt engineering and Retrieval‑Augmented Generation (RAG).
• Experience designing and evaluating hybrid search (semantic + lexical) using embeddings and vector databases.
• Hands‑on experience with agent frameworks (e.g., Google ADK, LangChain, LangGraph, AutoGen) in real‑world use cases.
• Proficiency with data analysis tools and a solid foundation in statistics.

Required skills

• Python
• Machine learning
• Natural Language Processing (NLP)
• Large Language Models (LLMs)
• Generative AI
• Prompt engineering
• Retrieval‑Augmented Generation (RAG)
• Hybrid search (semantic + lexical)
• Embeddings
• Vector databases
• Agent frameworks (Google ADK, LangChain, LangGraph, AutoGen)
• Data analysis tools
• Statistics