Computational Biologist at Tango Therapeutics
Cambridge, MA, US
Position Summary:

We are seeking an innovative, collaborative and enthusiastic computational scientist to work on a variety of high-dimensional bioinformatics projects centered on target identification, drug discovery and translational research. The individual will integrate internal and external datasets, including next generation sequence data. The successful candidate will be one who can develop novel methods, analysis strategies and tools to filter and distill multi-dimensional datasets to generate focused hypotheses to drive primary research. A critical component of the job will be the close collaboration with multi-disciplinary internal discovery teams and external collaborators. This individual will be a critical thought leader in the company, collaborating closely with discovery and development scientists.

Job Responsibilities:

Design and evaluate integrative approaches to the analysis of NGS cancer exome and transcriptome data, as well as other high-throughput data types
Apply machine learning/statistical-based approaches to establish and benchmark predictive models of biological/chemical data
Develop innovative, robust, analysis pipelines that can be applied in a research and clinical setting
Develop and contribute to external collaborations and partnerships
Liaise with lab scientists and software engineers as a project team member and provide expertise as a scientific resource
Working knowledge of oncology and/or immunology preferred, experience with planning of clinical trials a plus

Ph.D. in bioinformatics, computational biology, genetics or a related discipline + 3-5 years’ experience of applied research in either an academic or industry setting
Expertise in computational biology, genomics and other high-throughput data platforms with an aptitude to apply experimental methods to understand disease biology and drug discovery
Significant experience in the analysis of high-throughput DNA and RNA high-throughput sequencing data, including alignment, quality measurements, variant calling, fusion discovery and transcript quantification
Demonstrated ability to formulate and test hypotheses by designing and implementing computational approaches, ability to effectively interpret and communicate conclusions from complex data is essential
Other ideal areas of scientific expertise:
Fundamental statistics and machine learning applications to life sciences
Experience analyzing protein sequences
Predictive modeling, benchmarking
Experience with mining public data sets, such as TCGA
Technical proficiencies should include:
Linux in a grid and/or cloud environment, experience with cloud computing preferred
Proficient programming skills and computational analysis background
Familiarity and experience applying statistical fundamentals
Experience with R, PERL or Python, SQL are highly desirable
Distributed computing
Capacity to prioritize and work independently to complete tasks and advance projects with minimal supervision
Ability to work effectively with internal and external collaborators and multidisciplinary teams composed of scientists and non-scientists to translate emerging research to guide internal programs
Identify partners/consultants to complement internal bioinformatics efforts
Proficient written and verbal communication skills, particularly of complex information and concepts
Creative, innovative thinking