Associate Director, Data Science

Rhythm Pharmaceuticals•Boston, MA

7d•Hybrid

About The Position

We are seeking a highly motivated Associate Director of Data Science within Rhythm's Research group and the Data Sciences Team in support of our clinical, regulatory, and scientific objectives in the rare neuroendocrine/obesity/metabolic disease. The successful candidate will have a strong background in biostatistics, genetics, and data analytics, and will be responsible for implementing advanced AI data models, predictive tools, and integrative analyses across the obesity and metabolic disease therapeutic areas. A core focus of this position will be the development and implementation of algorithmic phenotyping approaches using electronic medical records (EMR) and real-world datasets, enabling robust patient stratification, cohort definition, and integration with genomics and biomarker data. This position is ideal for a technically strong investigator who thrives in a fast-paced environment and is motivated to apply and scale high-impact data science infrastructure alongside a growing team.

Requirements

Ph.D. in Biostatistics, Computational Biology, Genetics, Data Science, or related quantitative field.
~5+ years of relevant experience in biotechnology, pharmaceuticals, or healthcare analytics.
Experience with neuroendocrine, obesity/metabolic-related biology and datasets.
Experience applying machine learning and AI models to real-world and clinical datasets, including model development, evaluation, and deployment in production or near-production settings.
Experience developing or utilizing AI-driven agents/workflows to automate data extraction, phenotyping, analysis, or knowledge generation tasks.
Strong hands-on expertise in SQL, Python, and R, with experience building production-quality data pipelines.
Experience with cloud computing and storage environments including AWS, GCP, Snowflake.
Demonstrated experience with variant calling pipelines, variant interpretation and ACMG rare variant classification.
Demonstrated experience in EMR/EHR and real-world data analysis (e.g., UK Biobank, All of Us) including cohort building and longitudinal data modeling.
Proven track record in algorithmic phenotyping, including use of coding systems (ICD, CPT, SNOMED), clinical ontologies, and feature engineering.
Strong problem-solving skills and ability to operate independently in a fast-paced, execution-focused environment.
Excellent communication skills with the ability to clearly present complex analytical outputs to technical stakeholders.

Nice To Haves

Familiarity with broader bioinformatics/multi-omics methodologies including RNA-seq, methylation analysis, long-read sequencing would be advantageous.

Responsibilities

Design and deploy AI-driven, agent-based phenotyping pipelines that leverage EMR/EHR and real-world data to define disease cohorts, endpoints, and longitudinal outcomes.
Develop scalable approaches for cohort identification, feature extraction, and phenotype validation, including rule-based and machine learning methods.
Maintain high-throughput rare variant curation and classification models.
Execute the design, development, and deployment of data analysis pipelines, statistical models, and predictive tools to support Genetics-led programs.
Lead hands-on integration of clinical, EMR, genomics, and biomarker datasets, enabling multi-modal analyses.
Build and maintain reproducible workflows for data ingestion, harmonization (e.g., coding systems, ontologies), QC, and analysis (SQL, Python, R).
Apply statistical genetics and advanced analytics to link phenotypic definitions with genetic signals, including rare variant analyses.
Drive improvements in data infrastructure and phenotyping frameworks to support team expansion and increased dataset complexity.