AI/ML Clinical Data Science Intern

Lexeo Therapeutics • New York, NY

1d • $50 - $50

About The Position

Lexeo Therapeutics is a clinical-stage genetic medicine company headquartered in New York City, pioneering cardiac genetic medicine candidates to treat the root causes of inherited cardiovascular diseases. Our lead program, LX2006, targets cardiomyopathy associated with Friedreich’s Ataxia and anchors a broader pipeline addressing genetically defined conditions such as hypertrophic and arrhythmogenic cardiomyopathies. Backed by a strong financial foundation, Lexeo is positioned to translate groundbreaking science into durable clinical impact.

This internship sits at the intersection of artificial intelligence, machine learning, and clinical drug development. You will work directly with Lexeo’s clinical and scientific leadership to design and execute data-driven analyses using real clinical study data. The overarching goal is to generate novel insights that inform our understanding of:
Disease burden and progression in rare cardiovascular conditions
Mechanisms of action of AAV-based gene therapies in human subjects
Novel clinical endpoints and biomarkers that could strengthen future study designs
This is hands-on, hypothesis-driven R&D work. You will not be running pre-packaged reports or prompting general-purpose AI tools — you will be building and deploying analytical pipelines, training models, and contributing to scientific interpretation alongside domain experts.

Requirements

• Currently enrolled in a college or university (undergraduate or graduate level) in Computer Science, AI/ML, Statistics, Biostatistics, Bioinformatics, or a related quantitative field, OR enrolled in a biological or life science program with demonstrable, substantive experience in applied ML/AI through coursework, research, or prior internships
• Hands-on experience building, training, or deploying machine learning or AI models in an academic project, research lab, or prior work setting
• Proficiency in at least one of: Python, R, SQL, or Cypher for data manipulation and analysis
• Ability to work independently on open-ended analytical problems, make methodological decisions, and communicate trade-offs clearly

Nice To Haves

• Familiarity with clinical or biomedical data (EHRs, biomarkers, imaging, clinical trial datasets)
• Experience with Power BI or similar BI/visualization platforms
• Background in cardiovascular biology, rare diseases, or gene therapy
• Prior exposure to generative AI model development or large language model fine-tuning
• Experience working within regulated or GxP-adjacent data environments

Responsibilities

• Write scripts in Python, R, SQL, and/or Cypher to extract, join, and transform clinical data from internal and external sources
• Build and work within structured databases and data lakes to organize multi-modal clinical datasets
• Perform rigorous data validation, cleaning, and QC to ensure analytical readiness
• Train, validate, and deploy ML models — including supervised, unsupervised, and generative AI approaches — applied to clinical and biomarker data
• Apply advanced statistical techniques relevant to small-n clinical datasets, including mixed-effects models, survival analysis, and dimensionality reduction
• Evaluate model performance, interpretability, and clinical relevance in collaboration with scientific stakeholders
• Use analytical platforms such as Power BI, Excel, and Maxis to generate summaries, dashboards, and visualizations for cross-functional audiences
• Synthesize findings from LEXEO’s internal clinical studies alongside relevant external data sources
• Participate in working sessions with clinical scientists, statisticians, and CMC colleagues to discuss analytical direction and results

What This Job Offers

• Career Level: Intern
• Education Level: No Education Listed
• Number of Employees: 11-50 employees