Senior Data Scientist

Data Scientist – LLM Summarization / Conversation Intelligence

Location: Remote – U.S.

Employment Type: Contract-to-Hire

About the Role

We’re seeking a product-minded Data Scientist with strong expertise in large language models (LLMs) and natural language processing (NLP) to join an initiative focused on conversation intelligence in healthcare.

You’ll play a key role in evaluating and improving AI-generated clinical summaries — ensuring accuracy, factual consistency, and usability at scale. This is an opportunity to apply cutting-edge AI to make healthcare communication smarter and safer.

What You’ll Do

• Evaluate LLM-generated summaries of clinical conversations to detect missing details or hallucinations.
• Analyze unstructured text data (transcripts, notes, etc.) to assess model quality and performance.
• Design evaluation frameworks and scalable workflows for LLM testing and analysis.
• Collaborate with data scientists and product leads to translate complex findings into actionable insights.
• Work with engineers to support automation, pipeline optimization, and lightweight prototyping.

What You’ll Bring

Required Qualifications

• Strong proficiency in Python and ML/NLP libraries (e.g., PyTorch, TensorFlow, Hugging Face).
• Hands-on experience with LLMs (e.g., GPT, LLaMA, Mistral, Claude) or text summarization models.
• Familiarity with LLM evaluation — accuracy, hallucination detection, and factuality testing.
• Experience working with unstructured text data and large-scale NLP pipelines.
• Ability to contextualize technical results into product or business-level insights.

Preferred Qualifications

• Experience in healthcare data, clinical informatics, or AI scribe applications.
• Background in LLM summarization evaluation or hallucination mitigation.
• Knowledge of ML Ops concepts and scalable data workflows.