SimBioSys ( is seeking an exceptionally talented Junior Bioinformatics scientist to work on one of the most important challenges in medicine - improving outcomes in Cancer. SimBioSys is a technology company on a mission to deploy Computational Oncology to transform decision making and patient experience in Cancer Care. By virtualizing cancer, both clinicians and patients are empowered with a better understanding of the disease. Furthermore, our platform provides the opportunity to computationally assess the efficacy of all available treatment options to truly individualize treatment.

We are seeking candidates to investigate how intra- and inter-tumor heterogeneity contribute to patient-to-patient variability in response to therapy. The work will require the ability to integrate multi-omics data (genomic, transcriptomic, and proteomic) with patient phenotype data (age, weight, etc.) and patient-specific, spatially resolved models of tumor biology to understand how patient features work together to confer drug sensitivity or resistance. Experience working with heterogeneous data, like single-cell ‘omics, mathematical ecology, and epidemiology is a plus. Above all, ideal candidates should be creative problem-solvers, with a willingness to try a range of approaches to tackle each new challenge.

The position will require you to design and drive projects in which you will work closely with team members. Simulating and analyzing individual patient tumors using SimBioSys' TumorScope platform will facilitate your identification and development of novel, putative, computational biomarkers of Breast Cancer outcomes, prognosis, treatment response, etc. Fostering your analytical, biological, and computational skills, this position will provide you real world experience solving problems and developing putative biomarkers of Breast Cancer, while allowing you to contribute to the fight against cancer.

Required Qualifications

  • 0-2 years full time employment in industry or postdoc experience building and validating predictive models on structured or unstructured data
  • Strong background knowledge and experience in the field of cancer biology (those without cancer background need not apply).
  • PhD in a quantitative discipline (e.g. cancer biology/genetics, statistical genetics, machine learning/deep learning, bioinformatics, statistics, computational biology, biomedical informatics, or similar)
  • Strong programming skills in Python and R, data science-related libraries (also w/ Linux OS experience)
  • Expert-level data analytics skills, with a particular focus on detailed characterization of genomic, transcriptomic, radiomic, and clinical datasets towards biomarker development
  • Experience with supervised and unsupervised machine learning algorithms used in genomics and clinical research; regression, generalized linear models, mixed effect models, classification, survival modeling, clustering, dimension reduction, deep neural networks, decision trees, gradient boosting, etc
  • Excellent written and verbal communication skills
  • Ability to thrive in a fast-paced startup environment
  • Both flexible team player & independent senior researcher mindsets required

Desired Qualifications

  • Strong peer-reviewed publication record
  • Understanding of CAP/CLIA validation protocols and how to carry novel scientific discoveries to market
  • Experience working closely with institutional research groups towards the design and validation of computational predictions
  • Experience working with heterogeneous data, like single-cell ‘omics, mathematical ecology, and epidemiology
  • Experience mapping ‘Omics data to patient phenotypes
  • Strong mathematical and analytical skills