2 days ago
Gent, BelgiumStaff+
Responsibilities
- Automate and professionalize machine-learning and experimental-design pipelines for genomic target prediction.
- Migrate scripts and notebooks into production-ready, version-controlled codebases.
- Automate dataset preparation, configuration, and pipeline execution to reduce manual work.
- Integrate pipelines with AWS and HPC environments.
- Implement version control, testing, and reproducibility standards across ML workflows.
- Collaborate with wet-lab and computational biology colleagues to align pipelines with scientific requirements.
- Coordinate multiple projects, reassign tasks as priorities change, and present results to internal and external stakeholders.
Requirements
- PhD in bioscience engineering, bioinformatics, computer science, or machine learning engineering, or an MSc with 5+ years of equivalent experience.
- Strong Python skills and the ability to write readable, testable, reproducible code.
- Experience productionizing analysis code using Git, code review, packaging, Docker, Singularity/Apptainer, and automated testing or CI/CD.
- Hands-on experience with workflow orchestration such as Nextflow or Snakemake.
- Experience running workloads on AWS and/or HPC clusters such as SLURM.
- Knowledge of statistical modeling and machine learning applied to biological data, including model evaluation and experiment tracking.
- Ability to collaborate across engineering and bench-science disciplines.
- Eligibility to live and work in Belgium.
- Preferred experience with genomics and transcriptomics data, R, MLflow, Weights & Biases, Terraform, or client-facing consulting/CRO work.
- Fluent written and spoken English, with strong communication, analytical, and initiative-taking skills.
Benefits
- Hybrid work arrangement in Ghent, Belgium.
- Project-based work in a multidisciplinary biopharma data and analytics environment.