Bioinformatics Scientist - Machine Learning (ML/AI)

Description:

We are a team of highly experienced and collaborative bioinformaticians and we are seeking a qualified intern to help us leverage state of the art AI for healthcare. Your work will involve research and development of AI based bioinformatics applications for multiple kinds of biological data, particularly next-generation sequencing (NGS). Working on the crossroads of state of the art in AI and bioinformatics will equip you with the skills and experience of applying AI in improving patients’ lives.

We are seeking a highly motivated and analytical Bioinformatics contractor to join our computational biology team. In this full-time role, you will be at the forefront of liquid biopsy research. Your work will directly contribute to the computational development of our next-gen NGS assays, helping push the boundaries of personalized medicine.

Key Responsibilities

• Pipeline Execution & Optimization: Assist in developing, testing, and optimizing bioinformatics pipelines for the identification and quantification of genetic mutations from cfDNA NGS datasets.
• Data Visualization: Create clear, clarifying visualizations of genomic data, coverage maps, biomarker characteristics, to present findings to the cross-functional R&D team.
• Data Analysis: Analyze genetic mutations identified in cfDNA; propose and explore novel biomarkers; build reproducible machine learning models to quantitatively assess and validate biomarkers.
• Collaboration: Work closely with senior bioinformaticians to troubleshoot analysis strategies and correlate computational findings with clinical data.

Minimum Qualifications

• Education: Bachelor’s or Master’s degree or higher in Bioinformatics, Computational Biology, Computer Science, Biostatistics, or a closely related field.
• Programming Skills: Strong proficiency in Python and Bash/shell scripting within a Linux/Unix environment and familiarity with good engineering practices including proper use of generative AI, version control, and documentation.
• High-performance computing: Proficient in scaling bioinformatics pipelines across HPC clusters using Slurm or equivalent to accelerate NGS data processing.
• Genomic Fundamentals: Solid understanding of Next-Generation Sequencing (NGS) technologies, sequence alignment, and structural variant detection.
• Machine learning: Familiarity with common machine learning concepts, models, metrics and frameworks (scikit-learn, pandas etc).

Preferred Qualifications

• Familiarity with workflow management systems (Nextflow, Snakemake) and containerization (Docker, Singularity or equivalent).
• Prior exposure to liquid biopsy data (cfDNA/ctDNA) or cancer genomics.
• Strong track record of data analysis and publication in relevant fields is a plus.

Note: Our absolute priority is finding someone who is exceptionally strong in machine learning and algorithm development. We need someone who can work independently and has a deep, solid grasp of machine learning algorithm development. Specifically, we are looking for candidates with a strong academic background from a top university, or experience working at a reputable institute or company, with a proven track record in ML/algorithm development. Please prioritize technical depth and a strong professional and academic background over specific biology experience for the next batch of resumes. Let me know if you have any questions. Candidates with good publications regarding novel computational biomarker discovery, and/or ML+AI will be given prioirty consideration for interviews.

Work Location: This is an onsite role within the Mississauga Campus. Candidate will be required to work onsite at least 3 days every week.

AI Disclosure: This recruitment process will not use automated or AI-enabled tools to assist with application screening and scheduling. All hiring decisions are made by qualified human reviewers.