Jobs

Are you an NLP engineer with a passion for biomedicine? Are you frustrated by the sclerotic structures and misaligned incentives of the industry?  Do you have a track record of using machine learning to solve complex problems in the field of biomedicine? If so, come work with us at Weave. Weave is building a generative AI platform that will revolutionize how life science companies collaborate.

We are seeking a talented NLP engineer to join our team and help us push the boundaries of what is possible with machine learning in the field of biomedicine. As an NLP engineer, you will be responsible for designing, implementing, and evaluating state-of-the-art NLP models and solutions that address real-world challenges in the biomedical domain. You will work closely with our team of researchers and developers to build and deploy NLP systems that extract valuable insights from biomedical data, including electronic health records, scientific literature, and clinical notes.

To be successful in this role, you should be familiar to biomedical terminology, and a deep understanding of NLP techniques and machine learning algorithms. You should also have experience working with large datasets and be superb at coding in Python.

If you are a highly motivated and talented NLP engineer with a passion for biomedicine, please reach out – we’d love to work together.  Email us at join@weave.bio.

We are recruiting a software engineer (full stack developer) to join our multidisciplinary team. The incumbent will be responsible for the implementation of computational systems surrounding a novel diagnostic workflow that integrates genomic data produced in real-time. Under the supervision of the research director and in collaboration with local medical, laboratory and IT staff, the candidate will be responsible for developing “full stack” IT and software solutions for the processing, management and delivery of clinical reports in real-time.

About the team

Dr Martin Smith’s laboratory (www.therealsmithlab.com) harmonizes genomic technologies and artificial intelligence to realize the enormous potential of nanopore sequencing in precision medicine. Our research group specializes in the development and implementation of precise, practical and economical applications for nanopore sequencing in clinical, academic and commercial environments. In particular, the laboratory is currently focusing on the implementation of a new computational solution for rapid, precise and cost-effective diagnosis of pediatric leukemias based on real-time gene expression profiling (transcriptomics).

The Smith lab is part of the Cancer and Immune Disorders Research Axis of the CHU Sainte-Justine Research Centre and is affiliated with the bioinformatics program at the University of Montreal.

Work environment

The Sainte-Justine University Hospital Center (CHU) is the largest mother-child center in Canada and one of the four largest pediatric centers in America. Its 5,000 employees and 500 doctors, dentists and pharmacists work in a highly innovative and respectful environment, placing patients and their family at the heart of medical practice. Through its association with the University of Montreal, CHU Sainte-Justine is the largest pediatric training center in Quebec and a leader in Canada, welcoming over 4,000 students and interns each year.

The CHU Sainte-Justine Research Center hosts more than 1200 scientists, including over 210 principle investigators, 110 clinicians and more than 450 graduate and postdoctoral students. Driven by a vision of research excellence, the center strives to ensure that Quebec remains as world leader in healthcare and biomedical research benefiting mothers, children, and adolescents. The Centre’s mission is focused on advancing scientific knowledge while delivering faster and less invasive strategies for the prevention, diagnosis, prognosis, treatment, and long-term follow-up of patients–from the conception until adulthood.

Employment conditions

CHU Sainte-Justine Research Center Employees Union (SECR)
Reporting to: Dr Martin Smith
Type: Regular, full-time (35h/week)
Start date: Immediately
Duration of mandate: 2 years

Join “The Laboratory for RNA-Based Lifeforms” in University of Toronto’s Donnelly Centre. Together with Dr. Artem Babaian the work will develop the state of the art for the detection and sequence analysis of RNA viruses and virus-like agents.

(Micro)Biology is undergoing a paradigm shift in our understanding of Earth’s genetic diversity. This is being driven by the widespread adoption and exponential drop in cost of DNA/RNA sequencing, with 100+ petabytes of public sequence data available today, and growing. Our lab aims to pioneer a new-generation of computational analysis techniques optimized for exabase/exabyte-scale datasets.

Recently we’ve developed an AWS-cloud backed computing architecture, Serratus (https://github.com/ababaian/serratus), which has enabled us process 5.7 million datasets (10.2 petabases) in only 11 days. This analysis revealed 130,000+ novel RNA viruses across the world, where only 15,000 were previously known in public databases. Learn more in our first Nature paper, or watch our HCLS21 talk.

Position: Software Developer III
Site: MaRS Centre, Toronto
Department: Genome Informatics
Reports To: Director, Genome Informatics and Principal Investigator
Salary: Commensurate with level of experience
Hours: 35 hours/week
Status: Full-time, Permanent

We are growing! With new projects and lots of exciting technologies, the Ontario Institute for Cancer Research (OICR) is looking for a passionate and talented Software Architect to join the Genome Informatics team to continue building cutting edge tools and infrastructures used by researchers around the globe to fight cancer.

Our open source applications handle vast amounts of data (2+ PB) and run on large compute environments. Designed and implemented by our in-house developers, we maintain a diverse set of tools and projects, from complex ETL systems to modern user interfaces. The Genome Informatics team has worked on a variety of projects including:

• ICGC-DCC (github, application) – Our most mature and well known project is a submission system comprised of an ETL pipeline and data portal coordinating cancer research on 86 projects with participants from all over the world. With ICGC-ARGO ICGC is entering a new phase with an engaging and complex set of software engineering challenges ahead of us, such as providing researchers with access to 100’s of billions of genetic variants.
• ICGC-ARGO (github, application) – The next generation and evolution of the original ICGC-DCC, this platform aims to uniformly analyze specimens from 100,000 donors with high quality clinical data in order to address outstanding questions that are vital to the quest to defeat cancer.
• Cancer Genome Collaboratory (github, website) – A compute and storage cloud operated by the team which is progressively enhanced with more tools to assist researchers running analysis pipelines.

• VirusSeq Data Portal for COVID-19 (github,application) – The goal of the CanCOGeN VirusSeq project is to sequence up to 150,000 viral samples from Canadians testing positive for COVID-19 and make the sequences and associated non-personal contextual data available for research and exploration in an open-source and open-access data portal

• Human Cancer Models Initiative (HCMI) Catalog (github, application) – A searchable catalog of cancer models.

As part of the Genome Informatics team, the successful candidate will be joining some of the above-mentioned projects, but also be contributing to Overture.bio (github, website), our suite of open-source components for big data genomic science in the cloud.

We are looking for a passionate Software Developer/Architect to join our agile development team. In this role, you will serve as a technical guiding force for multiple ongoing projects as well as be responsible for spearheading and championing technical innovation. This would be an ideal position for a solid software developer who is looking to transition towards a software architect role.

New employees who may be required to work on-site are required to be fully vaccinated for COVID-19 subject to the duty to accommodate on the basis of protected grounds pursuant to the Ontario Human Rights Code.

Fully vaccinated is defined as having received all of the required doses of a Health Canada approved vaccine and having received the final dose at least 14 days before your employment start date.

As described above, the requirement to be fully vaccinated is subject to the Ontario Human Rights Code. If the candidate is unable to receive the COVID-19 vaccine for a reason protected by the Code, requests for accommodation from the vaccine policy will be assessed on a case-by-case basis.

To learn more about working at OICR, visit our career page.

Position: Software Developer I
Site: MaRS Centre, Toronto
Department: Genome Sequence Informatics
Reports To: Manager, Infrastructure & Software Development
Salary: Commensurate with level of experience
Hours: 35 hours/week
Status: Full-time, Permanent

We are looking for a passionate software developer to join the Genome Sequence Informatics (GSI) team!

GSI designs applications to streamline and automate analysis for the Genomics program (https://genomics.oicr.on.ca), controls the data life cycle, and creates useful and dynamic reports at scale. We ensure data flows smoothly, securely, and correctly from the lab through to the clinicians and researchers who use it. Our primary languages are Java, R, Python, Javascript, MySQL, PostgreSQL, and MongoDB and we use technologies like Docker, OpenStack, Prometheus.IO, Loki, Promtail, and Univa Grid Engine, and are expanding into Cloud environments like Microsoft Azure. Many of GSI’s software projects are open-source and available on GitHub: https://github.com/oicr-gsi/ and https://github.com/miso-lims.

GSI has three sub-teams:

• Infrastructure: Includes laboratory tracking, pipeline and data management, and reporting. This team develops the open source MISO LIMS (https://miso-lims.github.io) and associated applications, workflow systems like Vidarr and Cromwell (https://cromwell.readthedocs.io) to automate and streamline data analysis, tracking, and workflow management, and maintains a suite of specialized reports for quality control, forecasting, and lab operations.
• Analysis: Bioinformatics analysis and data release. Develops the analysis techniques and pipelines used by OICR Genomics for alignment, de novo assembly, variant detection, quantification of tumour heterogeneity and purity, RNAseq analysis, variant significance prediction, structural variant calling, immune detection, cfMeDIP, and others. This team also archives data for long-term storage and releases data to collaborators and public archives.
• Cancer Genome Interpretation: Validates pipelines for accreditation, analyzes and interprets genomic data using accredited pipelines and processes, and drafts reports for clinical cases.

Software developers in GSI are enthusiastic and autonomous. As part of the team, you will be involved in all aspects of development of new applications for high-impact cancer research and clinical reporting, as well as monitoring, diagnosing, and pushing fixes to improve stability and performance of existing applications. You will develop and improve our production system within a research environment.

New employees who may be required to work on-site are required to be fully vaccinated for COVID-19 subject to the duty to accommodate on the basis of protected grounds pursuant to the Ontario Human Rights Code.

Fully vaccinated is defined as having received all of the required doses of a Health Canada approved vaccine and having received the final dose at least 14 days before your employment start date.

As described above, the requirement to be fully vaccinated is subject to the Ontario Human Rights Code. If the candidate is unable to receive the COVID-19 vaccine for a reason protected by the Code, requests for accommodation from the vaccine policy will be assessed on a case-by-case basis.

To learn more about working at OICR, visit our career page.