Location: Toronto, Canada (in-person)
Position: Full-time
Why Ephla Bio
Ephla Bio is developing the future of personalized therapeutics. Our team works across the San Francisco Bay Area, New York, and Toronto.
We're early, ambitious, and moving fast. This role is a chance to build the computational foundation of a company working to change how cancer is treated. We offer a high-trust environment where people own their work end-to-end and can see its impact.
The Opportunity
Ephla Bio is looking for a bioinformatician to turn biological and experimental data into insights that guide therapeutic development. You'll build reproducible analysis pipelines, interpret complex datasets, and apply statistical methods to target prioritization, working closely with our scientific and infrastructure engineering teams.
In the first six months, success means delivering reproducible bioinformatics pipelines, generating actionable analyses from our high-throughput screening (HTS) dataset, and establishing a reproducible framework for target prioritization.
What You Will Own
Bioinformatics pipelines: Build and validate workflows from tumor/normal sequencing (WES/WGS, RNA-seq) through QC, somatic variant calling, VAF and clonality analysis (truncal vs. subclonal, adjusted for purity and copy number), HLA typing, expression quantification, and reporting, to the standard needed to support preclinical and clinical operations.
Screening analysis: Analyze our HTS data and other large-scale screens. Integrate them with public datasets (e.g. immunopeptidomics) and turn patterns into testable hypotheses.
Statistical rigor and validation: Assess assay quality, batch effects, and biological variability. Benchmark methods, validate findings against independent datasets or experimental results, and communicate uncertainty early.
Target prioritization: Combine assay results, sequence annotations, and relevant biological evidence to rank candidates and explain the rationale for experimental follow-up.
Lab partnership: Design experiments with lab scientists (scale, controls, data priorities), turn predictions into testable candidates, and feed results into the next round.
Tools that speed up decisions: Work with infrastructure engineers to build tools that let scientists explore data themselves. Maintain a shared, tested codebase with tracked data provenance and versioned analyses.
Communication beyond the team: Present findings to leadership, external collaborators, and partners. Contribute computational sections to study reports and regulatory documents as our programs advance.
Who You Are
Strong bioinformatics foundation: A track record of using computational analysis to answer biological questions. You have a PhD in bioinformatics, computational biology, or a related field, or a relevant graduate degree with equivalent research or industry experience.
Hands-on with high-dimensional data: Deep experience with one or more of NGS (DNA or RNA), single-cell, proteomics or immunopeptidomics, or functional screening data, from raw inputs through QC and biological interpretation.
Practical programming skills: Strong Python and/or R skills for biological data analysis and visualization. You write maintainable code and use version control, testing, and code review.
A pipeline builder: You've built and maintained pipelines other people depend on, managing metadata, provenance, dependencies, and growing data volumes. Pipeline work in a regulated or clinical setting (e.g. CLIA/CAP) is a strong plus.
Statistically rigorous: Strong grounding in experimental design, confounding, batch effects, and multiple testing. You can tell biology from an artifact and say how confident you are.
An owner and collaborator: You take ambiguous projects from idea to done, work fluidly across computation and biology, and adapt as evidence changes. You're curious and motivated by patient impact.
Nice to Have
Immunology or immuno-oncology: T cell biology, antigen processing and presentation, neoantigen prediction, HLA binding and presentation tools (e.g. NetMHCpan, MHCflurry), or TCR repertoire analysis.
Drug development experience: You've supported programs from discovery through lead nomination or IND, including IND-enabling study reports.
Applied ML: Training and evaluating predictive models on biological data with tools such as scikit-learn, R modelling packages, or PyTorch. You understand feature selection, cross-validation, and overfitting.
Deeper ML: Deep learning, pretrained or foundation biological models (protein language models, single-cell models), or protein structure tools, including using embeddings or fine-tuning for a specific task.