Data Science Intern (ATX24-07)

Description

This internship is primarily aimed at students in their second year of a Master’s program from engineering schools or universities.

As a Data Science Intern at AUROBAC, (1) you will take the lead in developing, implementing, and assessing machine learning tools for in-silico molecule screening. (2) You will engage in biomarker research projects by applying statistical methods to clinical and multi-omics databases. (3) Additionally, you will support the R&D and Business Development teams by providing insights through a range of statistical analyses.
The Data Science Intern will report to the Data Science Manager and collaborate closely with the scientific team responsible for drug pipeline development.

 

Missions

• Develop, implement and assess machine learning tools for in-silico molecule screening:
  – Maintain the training database up-to-date by incorporating the latest available data, enriching it with new sources, and performing data cleaning to ensure a high level of quality
  – Conduct a literature review to identify machine learning approaches tailored to the specific needs of the program
  – Implement such approaches and evaluate them, to surpass the performance of current models, particularly in the context of small datasets
  – Regularly apply these approaches within an experimental validation framework
  – Implement explainable machine
• Engage in biomarker research projects by applying statistical methods to clinical and multi-omics databases:
  – Help refine and specify research questions with the R&D team by providing statistical insights, including framing questions in quantitative terms
  – Participate in identifying relevant clinical and/or omics databases
  – Based on the project’s status, assist with data cleaning and apply statistical methods and machine learning algorithms to uncover biomarkers

 

Technical skills

• Strong understanding of core statistical concepts and methods, including key statistical tests and their applications
• Proficiency in Python, including standard data manipulation and visualization libraries (Pandas, Matplotlib, Numpy, Seaborn), as well as machine learning libraries (Scikit-learn, Pytorch, TensorFlow)
• Familiarity with basic Unix commands and environment is a plus
• Prior experience with omics data analysis would be a major plus

 

Personal skills

• Fluency in English is a must-have, French language skills would be a major plus
• Rigorous, with analytical skills, paying attention to details, able to synthesize information
• Excellent organizational and communication skills
• Ability to work both independently and collaboratively in a fast-paced research environment
• Ability to proactively identify and propose solutions to complex problems

 

Perks

“Titres restaurants” and catering available on site
Public transport participation
Access to gym and group classes
Concierge service

 

To apply, please send your CV and cover letter application to jobs@aurobac-tx.com mentioning the reference ATX24-07.

For more information on how we process your personal data, please visit this link

2024.10.18 ATX24-07 Data Science Intern 6 months ad