Senior Data Scientist III - Agentic AI

Our client is a leading global provider of legal, regulatory and business information and analytics that help customers increase productivity, improve decision-making and outcomes, and advance the rule of law around the world.

They help lawyers win cases, manage their work more efficiently, serve their clients better and grow their practices. They assist corporations in better understanding their markets, monitoring their brands and competition, and in mitigating business risk. They collaborate with universities to educate students, and support nation-building with governments and courts by making laws accessible and strengthening legal infrastructures. They partner with leading global associations and customers to collect evidence against war criminals and provide tools to combat human trafficking.

Responsibilities:

• Lead experimentation and model development for AI/ML solutions in legal products.
• Design and evaluate NLP, LLM, and generative AI approaches (e.g., RAG, prompt strategies).
• Define agentic workflows and reasoning strategies for multi-step legal tasks.
• Define retrieval strategies, including hybrid search (semantic + lexical), and evaluation metrics (e.g., relevance, ranking quality).
• Analyze large-scale legal 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, legal experts, and engineers to align solutions with user needs.
• Mentor team members and provide technical leadership in data science and AI.

Requirements:

• Bachelor’s or Master’s degree in a relevant field (e.g., Computer Science, Data Science, Statistics, Mathematics).
• Strong experience in machine learning, NLP, and LLM-based modeling.
• Proven experience designing and running experiments, including model evaluation and iteration.
• Experience with generative AI techniques (e.g., prompt engineering, RAG).
• Experience designing and evaluating hybrid search (semantic + lexical) using embeddings and vector databases.
• Experience designing agentic workflows and reasoning strategies, with hands-on experience applying agent frameworks (e.g., LangChain, LangGraph, AutoGen) in real-world use cases.
• Proficiency in Python and data analysis tools.
• Ability to define retrieval strategies, including hybrid search (semantic + lexical), and evaluation metrics (e.g., relevance, ranking quality).
• Able to analyze large-scale legal datasets to extract insights and improve model performance.