Bioinformatics scientist (cancer imaging)

Deadline: 19 February 2023

Employment term: Permanent

Category: Software development

Job type: Full time

Location: Yerevan

Job description:

BostonGene is opening a position at Biomedical imaging team. You will work with imaging data of different modalities, immunohistochemistry, multiplex fluorescence. Produce statistical analysis, create production ready data pipelines, and integrate it with R&D and clinical systems.

We offer:

The office is located in Yerevan, Armenia, company supports relocation, we provide airplane tickets, hotel accommodation for two weeks, full support in official paperwork, and work permits in Armenia;
Competitive salary and medical insurance;
Full-time position, permanent contract, flexible working hours;
Versatile professional environment: bioinformatics, biologists, physicians, and software developers who united to save people’s lives.

Job responsibilities

Work on semantic and instance segmentation models for histological images (H&E, MxIF & IHC) for tissue features and cell instances;
To design and implement segmentation techniques for histological images (MxIF and H&E), and create an automated system for classifying cells;
Work on cell classification approaches: clusterization, reference atlas creation, and classification approaches;
Work on cell community detection models (graph clustering approaches);
Work on research collaboration projects with leading American hospitals and institutions, provision of visualization and statistical data analysis;
Work on large image viewing and annotation tools, work on formats for fast large image processing;
Creation of distributed data processing pipelines.
Present your work internally and share key results with the team on a regular basis.

Required qualifications

knowledge of python and common data processing and machine learning libraries: numpy, pandas, scipy, scikit-learn;
experience with data visualization using matplotlib, Dash or other libraries;
knowledge and experience in statistical and data mining techniques: GLM/Regression, Random Forest, Boosting, Trees;
experience with relational databases, knowledge of SQL;
experience with processing of single cell data or spatial transcriptomics data;
experience with deep learning frameworks would be a bonus, pytorch or tensorflow.