Senior Data Scientist

Job Summary

To support rare disease research initiatives, the remote Senior Data Scientist will build agentic AI systems that facilitate multi-turn workflows, ensuring accurate data capture and interpretation while collaborating with NIH program staff and clinical experts.

Key Responsibilities

• Build agentic AI systems for rare disease research workflows, including conversation logic and confirmation steps
• Model outputs in Pydantic, ensuring structured output and validation of data
• Write and test prompts for clinical and scientific reasoning tasks, treating them as code with version control

Required Qualifications

• Bachelor's degree in Data Science, Computer Science, Bioinformatics, Biomedical Informatics, or a related field; advanced degree preferred
• At least 5 years of experience in building and operating production software or data systems, with 2 years focused on LLM-powered applications
• Experience with structured output and tool or function calling for model validation
• Ability to evaluate systems with no single right answer using methods like golden sets and regression suites
• Capability to manage a service end to end, from schema design through deployment and operation