Staff Research Scientist, Computational Toxicology

Summary

Join SandboxAQ, a high-growth company delivering AI solutions, as a Bioinformatician. You will develop novel computational tools to reshape drug discovery using deep learning models for genomics and transcriptomics. Responsibilities include developing and applying deep learning models to predict genomic and transcriptomic profiles, curating high-quality datasets, collaborating with a cross-functional team, and contributing to publications and patents. A Ph.D. in a relevant field and 2+ years of industry experience in deep learning for biopharma are required. Preferred qualifications include postdoctoral training and experience with long-context sequence modeling. The company offers competitive salaries, stock options, generous learning opportunities, comprehensive benefits, and a supportive work environment.

Requirements

• Ph.D. in a field setting you up to work on deep learning models for genomics, transcriptomics, and biological pathway modeling: computational biology, bioinformatics, computer science, applied math, etc
• 2+ years working on deep learning for biopharma in an industry context
• Experience in training, applying, and optimizing contemporary deep learning models, including generative models, as demonstrated by
• Experience applying deep learning models to problems in biopharma: genomics, transcriptomics, spatial transcriptomics, and/or related fields such as structural biology
• Software skills: advanced proficiency with Python, with related software ecosystem tools (i.e. Git, Docker, Kubernetes, etc), and contemporary deep learning and informatics terms (i.e. R, Pytorch, etc)
• Excellent communication skills

Responsibilities

• Develop and apply deep learned models to predict genomic and transcriptomic profiles, including after perturbation by drug molecules
• Drive curation and use of high-quality datasets, such as single-cell RNA-seq datasets
• Work with a cross-functional team of experts to computerize drug discovery
• Write patents, research papers and technical documents. Participate and present at international conferences
• Reshape drug discovery, advance machine learning, and protect humanity from disease

Preferred Qualifications

• Relevant postdoctoral training
• Experience in long-context sequence modeling
• Direct experience in drug discovery or development
• Experience running deep learning workloads on GPU clusters at large scale
• Experience working on cloud
• Contributions to open source repositories

Benefits

• Medical/dental/vision
• Family planning/fertility
• PTO (summer and winter breaks)
• Financial wellness resources
• 401(k) plans
• Competitive salaries
• Stock options depending on employment type
• Generous learning opportunities