Computational Scientist

Tailored Management; South San Francisco (CA); On-site; USD 51,000 - 73,000; Full time

Benefits offered by this job

Weekly Pay

Medical Insurance

Dental Insurance

Vision Insurance

Job summary

Tailored Management seeks a Computational Scientist to support the Regev Lab in analyzing large-scale multimodal perturbation datasets. You will develop, train, and evaluate deep learning models to understand how dataset components affect performance and learning outcomes.

You will work with large-scale experimental datasets, compare model outputs to experiments, and generate insights to drive improvements.

Qualifications

• PhD in a computational discipline or equivalent research experience.
• Preferred: Computational Biology, Computational Sciences, Statistics.

Responsibilities

• Train, develop, and evaluate deep learning models using large-scale multimodal perturbation datasets.
• Analyze how different subsets and components of datasets contribute to model learning and overall performance.
• Design and execute controlled training and testing experiments.
• Evaluate model predictions and outputs against experimental data.
• Perform statistical analysis to assess model performance and validate findings.
• Work with existing analysis codebases and cluster computing infrastructure.
• Maintain reproducible, well-documented, and structured analytical workflows.
• Collaborate with project lead and research team to deliver milestones.

Skills

PyTorch

Train/Test Split

Statistics

Python

Reproducible workflows

Education

PhD in computational discipline

Computational Biology

Computational Sciences

Statistics

Tools

NumPy

Scanpy

AnnData

SLURM HPC

Job description

Pay Rate: $36.97– $52.88/hour + Benefits

Benefits: Weekly Pay, Medical, Dental, and Vision Insurance

Contract Duration: 12 Months (Potential for Extension)

Position Overview

We are seeking a skilled Computational Scientist to support the Regev Lab in analyzing large-scale multimodal perturbation datasets. The primary focus of this role is to develop, train, and evaluate deep learning models to understand how different components of multimodal datasets contribute to model performance and learning outcomes.

The selected candidate will work with large-scale experimental datasets, assess model outputs against experimental findings, and generate insights to improve model performance and reliability.

Key Responsibilities

• Train, develop, and evaluate deep learning models using large-scale multimodal perturbation datasets.
• Analyze how different subsets and components of datasets contribute to model learning and overall performance.
• Design and execute controlled training and testing experiments.
• Evaluate model predictions and outputs against experimental data.
• Perform statistical analysis to assess model performance and validate findings.
• Work with existing analysis codebases and cluster computing infrastructure.
• Maintain reproducible, well-documented, and structured analytical workflows.
• Collaborate directly with the project lead and research team to deliver defined project milestones.

Required Education

• PhD in a computational discipline or equivalent research experience.
• Preferred academic backgrounds include:
• Computational Biology
• Computational Sciences
• Statistics

Required Technical Skills

• Hands-on experience training and evaluating deep learning models using PyTorch.
• Experience designing and executing controlled train/test split experiments.
• Familiarity with SLURM-based high-performance computing (HPC) clusters.
• Strong applied statistics and analytical skills.
• Proficiency in scientific Python libraries, including:
• NumPy
• Scanpy
• AnnData
• Experience developing reproducible, well-documented scientific analysis workflows.

Preferred Qualifications

• Experience working with single-cell transcriptomics data.
• Experience analyzing CRISPR perturbation screens, including Perturb-seq or similar technologies.
• Familiarity with representation learning techniques.
• Experience or familiarity with image analysis.