Senior Data Scientist (LLM & Clinical NLP)

Quick Facts

• Senior Data Scientist focused on LLM and Clinical NLP

Description

You will build and improve language-model pipelines that extract reliable, structured facts from messy clinical notes. The work includes rigorous evaluation, fine-tuning, deployment, and monitoring in production, with outputs feeding research studies and commercial real-world evidence data products. You will collaborate with Medical and Product teams to turn clinical questions into concrete model and data requirements.

Responsibilities

• Build and improve LLM- and transformer-based extraction pipelines (NER, text classification, relation extraction)
• Evaluate models with gold-standard datasets, error analysis, and trusted metrics
• Fine-tune, deploy, and monitor models in production
• Translate clinical questions into concrete data and model requirements with Medical and Product teams
• Present results and trade-offs clearly to technical and non-technical audiences

Requirements

• Master’s degree or PhD in a quantitative field (computer science, machine learning, data science, biostatistics, or similar); PhD welcome but not required
• ~5 years of hands-on data science or ML work, including models shipped on messy real-world data
• Hands-on transformer NLP (BERT/RoBERTa-family; biomedical/clinical variants like BioBERT/ClinicalBERT) for NER, classification, or relation extraction using Hugging Face Transformers
• Hands-on generative LLM work: prompt design with structured outputs, fine-tuning (e.g., LoRA/PEFT), RAG, and scalable evaluation (gold sets, error analysis, LLM-as-judge)
• Rigorous evaluation mindset to determine whether a model is actually correct
• Strong Python and SQL
• AI-native workflow using tools such as Claude and Cursor
• Fluent English and confidence presenting to cross-functional, non-technical stakeholders

Benefits

• Unrestricted AI stack and premium gear (e.g., paid Cursor and Claude Pro licenses)
• Remote-first autonomy with focus on shipped production systems
• Direct impact through close collaboration with executive leadership
• Frontier engineering culture and continuous growth/knowledge sharing