Role: Senior Data Scientist

Remote 

Looking Strong Candidates 

About the Role

LN is looking for Senior Data Scientist in a small team focused on applying AI to help legal professionals stay current as laws and regulations change. In this role, you will guide the development of large language models (LLMs) and build enrichments processing agents that analyze new and updated case law and legislation and support automated updates to impacted content. You will work within a shared Agentic Content Platform, partnering closely with platform and software engineering teams who are responsible for deploying models into production. Your focus will be on model design, evaluation, and AI Enrichments quality, while ensuring solutions are designed to integrate smoothly into the platform.

What You’ll Do

Serve as the primary senior data scientist, coordinating the work of a small team of data scientists responsible for designing and delivering LLM-based models and AI Enrichments.

Define and oversee AI workflows for legal research, impact analysis, and content update recommendations, ensuring high accuracy and editorial quality.

Design models and agentic or multi-agent LLM workflows that are ready for deployment by software engineers into the Agentic Content Platform.

Partner with platform and software engineering teams to align on interfaces, constraints, and integration requirements.

Collaborate with other teams to align approaches, reuse patterns, and share learnings.

Establish clear standards for model evaluation, quality thresholds, and handoff criteria from data science to engineering.

Provide hands-on technical guidance and mentorship to ensure the team operates cohesively and efficiently.

Serve as the primary technical point of contact for data science within cross-team platform discussions.

What You Bring

Master’s degree with 5–7 years of experience, or PhD with 2+ years of experience, in a quantitative field.

Strong experience working with large language models and transformer-based architectures (e.g., GPT-style models, BERT, T5).

Hands-on experience applying LLMs such as ChatGPT, GPT-4/3.5, Claude, or Mistral in applied or production-adjacent environments.

Experience designing agentic or multi-agent LLM workflows for research, drafting, and automated review, with attention to reliability and evaluation.

Experience with retrieval-augmented generation (RAG), semantic search, and vector-based retrieval.

Proven ability to collaborate effectively with software engineers and platform teams.

Strong communication skills and experience leading small teams in cross-functional environments.

Nice to Have

Experience working within shared AI platforms or centralized ML infrastructure.

Experience with legal, regulatory, or professional services content.

Familiarity with human-in-the-loop or editorial review workflows.

For this role, I’m specifically looking for candidates with strong hands-on experience in developing data models, training data set, evaluation of data quality, building Agents, working experience with NLP, LLMs, and strong background in AWS.