Python Phd Hpc Jobs in Plano, TX (NOW HIRING)

An Affiliate of Colossal is seeking a talented computational biologist with strong analytical skills to tackle challenging genotype-to-phenotype questions. The successful candidate will collaborate with scientists and engineers to design and perform bioinformatics analyses and integrate genomic, epigenomic, transcriptomic, and proteomic datasets to support de-extinction efforts. The candidate must have experience in bioinformatics, computational biology, statistics, or comparative genomics.

Preference will be given to candidates with a PhD who have demonstrated experience leveraging and interpreting machine learning / artificial intelligence frameworks to link genotype and phenotype using diverse comparative or functional genomic data and information in data-sparse or non-model organisms.

**This position will be based on-site in our Dallas, TX headquarters. Relocation assistance is available**

Duties and Responsibilities:

• Build machine learning or artificial intelligence models using diverse, integrative datasets
• Run comparative, functional, and statistical genomics analysis
• Run data analysis with biological data
• Develop new tools in R/Python for data analysis and visualization
• Curate and document raw and intermediate data and analysis software
• Prepare reports and presentations to communicate findings to wet-bench biologists and leadership

Required Skills and Abilities:

• Two years of bioinformatics experience in the following areas: Applied Statistics or Machine Learning / Artificial Intelligence in Genomics, Comparative Genomics, Functional Genomics / Multi-Omics, or Molecular Evolution. 
• Demonstrated ability building and training ML/AI models linking genotype and phenotype (e.g., sequence-to-function models) and experience with the popular libraries like Pytorch, Tensorflow, or OpenCV.
• Capable of leveraging and integrating knowledge across multiple levels of biological organization to validate the outputs of complex analyses.
• Demonstrated 2 years of experience with scripting languages, including but not limited to: Python, R, Perl, Ruby, Java, and BASH.
• Ability to write and run custom bioinformatics scripts using existing published tools and occasionally tools developed to summarize the results in a digestible manner and deliver the information using established reporting procedures.
• Proficiency with handling large-scale genomic data in an HPC (SGE, SLURM, PBS) Linux and/or cloud environment (e.g. AWS, Google Cloud, Azure).
• Experience in using GIT version control software and maintaining well-documented, reproducible notebooks and workflows.
• Ability to design and maintain databases (MySQL, PostgreSQL, MongoDB) and connect with visual platforms to curate and share data with non-bioinformatics team members.

Preferred Skills and Abilities:

• Developing or implementing AI/ML frameworks and systems biology networks (e.g., interpretable aka visible deep neural networks like GenNet) for genotype-to-phenotype and functional predictions
• Executing rigorous analyses of diverse functional epigenomics approaches (e.g., RNA-seq and ATAC-seq) and integrating multi-omics datasets to aid in understanding of gene expression regulation
• Performing evolutionary and statistical genomics analyses, including population genetics analysis (e.g., runs of homozygosity and association mapping), genome-wide scans for evolutionary signatures and selective sweeps, and comparative genomics analyses associating genotype and phenotype (e.g., PAML inference of molecular evolution and phylogenetic regression)
• Constructing, interpreting, and utilizing pangenome graphs, whole genome alignments, and gene homology relationships
• Calling germline and somatic sequence variants from high-coverage WGS, low-coverage WGS with imputation, and sequencing libraries from degraded or ancient DNA
• Statistical planning and collaboration with laboratory scientists on designing well-powered experiments to generate useful multi-omics data sets
• Understanding of precision gene editing technologies like CRISPR/Cas9 systems

Education and Experience:

• Masters with 2 years of relevant post-graduation work experience or PhD in quantitative or basic science (computer science, computational biology, bioinformatics, chemistry, physics, or mathematics/statistics preferred) is required