Senior Applied AI Data Scientist

Flatiron Health

Location

New York, NY

Job Type

Full-time

Posted

June 14, 2026

Views

Job Description

Flatiron Health seeks a Senior Applied AI Data Scientist to advance machine learning and generative AI applications in oncology research. The Discovery team develops next-generation research data products by applying ML and LLMs to extract clinical information from unstructured medical notes, creating de-identified datasets for cancer research.

Key Responsibilities

Apply existing AI systems to convert raw clinical data into high-quality research datasets
Develop subject matter expertise on data capabilities and collaborate on model enhancement
Partner with research scientists and oncologists to validate models for sound scientific insights
Define requirements for training and evaluation datasets
Provide analytical support and custom data outputs to cross-functional teams
Work with engineers on productionization and monitoring

Requirements

5+ years as applied data scientist or similar technical role
Understanding of ML/AI system measurement and quality assessment
Proficiency in Python (pandas/polars), SQL, and version control
Strong communication and cross-functional leadership abilities
Healthcare data experience preferred
Experience with bias risks, health equity, or underrepresented populations valued

Location: New York (hybrid, 3 days in office).

Frequently Asked Questions

Where is the job located, and what is the work-mode policy?

The position is based in New York, NY, and operates on a hybrid model requiring 3 days in the office.

What are the key responsibilities of this role?

You will apply AI systems to convert clinical data into research datasets, collaborate on model enhancement, partner with research scientists and oncologists to validate models, define training and evaluation dataset requirements, provide analytical support, and work with engineers on productionization and monitoring.

What qualifications and experience are required?

You need 5+ years of experience as an applied data scientist or in a similar technical role, proficiency in Python (pandas/polars), SQL, and version control, and an understanding of ML/AI system measurement. Strong communication skills are required. Healthcare data experience and familiarity with bias risks or health equity are preferred.

What team will I be working with?

You will be working with the Discovery team, which develops next-generation research data products by applying ML and LLMs to extract clinical information from unstructured medical notes.