At Synthetic Genomics, Inc., we are dedicated to developing and commercializing genomic-driven solutions to address global challenges. We are currently seeking a Bioinformatics Scientist to join our fast-growing, dynamic and collaborative team in La Jolla, CA.
The Bioinformatics Scientist will be part of the Computational Biology Group with primary focus on novel gene discovery and characterization. The successful candidate will be responsible for the development of automated cloud-based NGS pipelines as well as machine-learning models for the analysis of large microbiome datasets. These analysis pipelines and applications will be based on existing tools and algorithms as well as newly developed solutions tailored to address specific research goals. They will be integrated into Archetype®, SGI’s proprietary genome annotation and analysis web portal. This role requires strong programming skills, experience with NGS analysis tools, and expertise in classical machine-learning and deep-learning frameworks.
- Must be familiar with publicly available bioinformatics tools, algorithms, and websites.
- Strong programming skills in R and Python.
- Proven ability to train and evaluate classical machine learning models, such as linear and logistic regression, SVMs, Random Forests, and Gradient Boosting, as well as deep-learning models.
- Proficiency in working with databases and data management platforms (ex. SQL/NoSQL)
- Comfortable working with command line tools in a Linux shell environment.
- Must demonstrate a solid scientific proficiency, creativity, ability to collaborate effectively with others, and independent thought processes.
- Must feel comfortable working in a small team with extensive interactions with scientists inside and outside the organization.
- Must be capable of working on problems of diverse scope in which analysis of data requires a detailed evaluation of possible factors.
- Must be a team player and a focused individual with a strong work ethic and great attention to detail.
- Must exhibit excellent communication skills and a broad knowledge of the company’s technologies. Able to distill and relay complex scientific concepts to a variety of members within the organization.
- The Scientist is expected to be or become familiar with the background knowledge and technology required to address the goals of a program or research task.
- Strong communication skills.
- PhD in Bioinformatics, Computer Science, Statistics, Genomic Sciences, Molecular Biology, Genetics, Microbial Ecology or a related field.
- At least three years of experience in bioinformatics software development and research.
- Experience in NGS data analysis, including algorithm development, genome and metagenome assembly and annotation, microbial community profiling using 16S and ITS amplicon data, and development of statistical reporting tools.
- Experience developing, training, and evaluating deep-learning models using public DL frameworks, such as TensorFlow, Keras, PyTorch, Theano, Caffe, or Neon.
- Strong experience developing tools in programming languages such as Python, R, C++, Java, Perl, or Matlab.
- Experience with general NGS data analysis tools such as SAMtools, pysam, Picard Tools, Bowtie, BWA, and CLC Genomics Workbench.
- Experience with genome and metagenome assembly tools such as Celera WGS assembler, Canu, Velvet, SPAdes, IDBA-UD, MEGAHIT.
- Proven ability to independently manage several distinct projects at once.
- Ability to exercise judgment within broadly defined practices and policies in selecting methods, techniques, and evaluation criteria for obtaining results.
- Experience with microbiome analysis tools, such as mothur, QIIME, UPARSE, Swarm, vegan, metagenomeSeq, phyloseq.
- Knowledge of metagenome contig binning tools, such as CONCOCT, GroopM and MetaBAT.
- Experience developing R/Shiny apps.
- Experience working with Docker containers and cloud-based compute environments.