Genomic Data Scientist, Scientific Product

Key Skills

Python Programming, Scala Programming, C++, Java Programming, Machine learning techniques, Data science techniques, SQL, Apache Hadoop, MapReduce, TensorFlow, PyTorch

Job Description

You will be part of a small, science-driven product and engineering team that is building the data, analysis, and visualization solutions to accelerate translational research involving multi-omic and clinical data. You will be responsible for working on the end-to-end experience for common scientific applications that our users desire solutions for. For example, you could be responsible for developing an end-to-end solution for scalable transcript quantification. In this role, you would:

• study existing and cutting edge methods developed to solve the problem
• anticipate the scale our users may want to run at
• work with engineers to help implement a solution on the platform

You have experience with -omic data at scale and have worked on systems using a variety of technologies and processes. You are passionate about working with, and enabling access to complex molecular and clinical data, and want to build productized solutions.

Responsibilities:

• Periodically read and analyze research publications to identify useful methods
• Understand data scaling pain points and solutions for working at scale
• Build and maintain internal and external packages for Python and R
• Build and maintain scientific apps which operate on top of scalable infrastructure
• Replicate and reproduce identified methods of interest on the DNAnexus platform
• Partner with clients to understand their use cases and guide their analysis goals
• Based on analysis performed, identify product improvement opportunities for our core product and detail solution approaches.
• Designing and implementing asynchronous apps using the DNAnexus framework, from concept to production, while leveraging single and multi-node support with high quality, performance tested automated tests

Requirements:

• Team-oriented, with strong communication skills
• Strong scientific and computer science background
• Demonstrated ability to pick up new technologies and quickly adapt to new paradigms
• Fluent in Python, R, and/or bash scripting
• Experience using Linux and comfortable working in a Unix shell
• Solid understanding of the concepts of genomics and molecular biology
• Masters or Ph.D. in a computational or scientific degree
• (e.g. Computer Science, Computational Biology)

Qualifications

Desired Skills and Experience:

• 3+ years of experience in bioinformatics, biostatistics, genomics, statistical genetics, population genetics, systems biology, and/or translational research in either academic or industry settings
• 3+ years of experience with large-scale molecular/health data (ENCODE, 1000 Genomes, ExAC/gnomAD, TCGA, RNA-seq, ChIP-seq, etc)
• Deep knowledge of data-driven research in the health space (Healthcare, Healthtech, Biotech, etc)
• Well-versed in modern computational biology tools (BCFtools, PLINK, Hail, Glow, etc), programming stack (Python, R, SQL, bash), and statistical models and methods used to derive insights and make predictions (Polygenic Risk Score Analysis, GWAS, PCA, pathway analysis, etc)
• Experience with cloud computing, big data analytics technologies (Spark, Hive, Hadoop, etc), and an understanding of relational database concepts
• Ability to organize, plan, and execute rigorous statistical analysis on complex, multi-omic population-scale health datasets
• Experience translating scientific results and/or tools into products using an analytical and modular framework
• Ability to communicate complex scientific concepts to a range of technical and non-technical audiences
• A passion to build reliable products for the scientific community