Computational Scientist - Deep Learning & Computational Biology

Rose International; South San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

Rose International is seeking a highly qualified computational biology scientist to train and evaluate deep learning models on large multimodal perturbation datasets, using PyTorch on a SLURM cluster.

You will apply strong statistics and reproducible Python data analysis (numpy, pandas, scanpy/anndata) to characterize data contributions to model learning and collaborate with the Regev lab to align model outputs with experimental results.

Qualifications

• PhD in a computational discipline (computational biology, computational sciences, statistics or ML)
• Experience training deep learning models in PyTorch and evaluating with controlled train/test splits
• Proficiency in Python for data analysis (numpy, pandas, scanpy/anndata) with reproducible pipelines

Responsibilities

• Train and evaluate models on large multimodal perturbation datasets to understand data contributions to model performance
• Evaluate model outputs against experimental data from published datasets (Regev lab)
• Collaborate with researchers to interpret results and ensure reproducibility

Skills

PyTorch deep learning

Applied statistics

Python data analysis (numpy, pandas,/)

reproducible research

Education

PhD in computational discipline / computational biology / computational sciences / statistics / machine learning

Tools

SLURM cluster

Job description

Education

• PhD in a computational discipline or Computational Biology, Computational Sciences, Statistics or Machine Learning

Required Skills

• Training and evaluating deep learning models in PyTorch, including designing and executing controlled train/test split experiments on a SLURM cluster.
• Strong applied statistics
• Proficient scientific Python (numpy, pandas, scanpy/anndata) and reproducible, documented analysis practice.

Preferred Skills

• Experience with single-cell transcriptomics
• Experience with analysis of CRISPR perturbation screens (perturb-seq or similar).
• Familiarity with representation learning
• Familiarity with image analysis

Responsibilities

• Multimodal perturbation datasets are becoming increasingly large and available, and understanding which data contribute most to model performance is an increasingly important question.
• The Regev lab has generated a large multimodal perturbation dataset. The contractor will train and evaluate models on this data to characterise how different portions of the dataset contribute to model learning, and will evaluate model performance and model outputs against experimental data.
• **Only those lawfully authorized to work in the designated country associated with the position will be considered.**
• **Please note that all Position start dates and duration are estimates and may be reduced or lengthened based upon a client’s business needs and requirements.**

About Rose

• Founded in 1993
• Office Locations Across the U.S.
• 150+ Clients: Corporations and Government Agencies
• Employee Oriented Company
• Challenging Assignments Across the U.S.
• Continuous Professional Development

EMPLOYEE COMMENTS

• We want you to work with us, but don't take our word for it. Take a look at this sampling of employee comments. They speak for themselves.