Senior Scientific Data Scientist

<p><strong>Senior Scientific Data Scientist / Pipeline Engineer</strong><strong> Remote / Hybrid Oxford</strong><strong> 6 Month Contract</strong><strong> Outside IR35</strong><strong> £400 to £550 per day</strong></p><p><strong>Overview</strong></p><p>A technology-enabled drug discovery company is looking for a Senior Scientific Data Scientist to design, build and maintain the analytical pipelines that power its data-driven discovery platform.</p><p>The business combines automated wet-lab experimentation, proprietary analytical pipelines and deep scientific expertise to generate high-quality, reproducible biological datasets at scale. This data supports AI-driven discovery work across areas including oncology, immunology and neurodegeneration.</p><p>This role would suit a scientist-turned-coder or scientific data scientist with strong Python skills, statistical modelling experience and a background working with bioassay or experimental biology data.</p><p><strong>The Role</strong></p><p>You will build and improve Python-based analytical pipelines for diverse bioassay datasets, including biochemical, biophysical and cell-based assays.</p><p>You will work closely with wet-lab scientists to understand assay logic, experimental design and data handover processes, then translate those workflows into automated, reproducible analysis pipelines.</p><p>The work will involve dose-response modelling, curve fitting, QC, normalisation, plate-level statistics and data validation, helping scientists generate clearer, faster and more reliable insight from complex experimental data.</p><p><strong>Key Responsibilities</strong></p><ul><li>Build, maintain and extend Python-based analytical pipelines for bioassay datasets</li><li>Develop statistical and modelling workflows, including dose-response modelling, 4PL curve fitting and mechanistic models</li><li>Build QC, normalisation and data validation frameworks for experimental biology data</li><li>Support plate-level statistics and analysis of high-throughput assay outputs</li><li>Translate wet-lab scientific workflows into reproducible automated pipelines</li><li>Improve data structures, file preparation and analysis readiness</li><li>Partner with wet-lab scientists to understand assay design and experimental logic</li><li>Clearly communicate analytical choices, QC decisions and modelling approaches</li><li>Build robust, documented and reusable scientific software</li></ul><p><strong>Essential Skills</strong></p><ul><li>Strong Python experience for scientific computing</li><li>Experience with Pandas, NumPy, SciPy and visualisation libraries such as Matplotlib or Seaborn</li><li>Experience analysing bioassay, assay or experimental biology data</li><li>Understanding of dose-response modelling, curve fitting, 4PL, EC50 / IC50 or similar</li><li>Experience with QC, normalisation, data validation or plate-level statistics</li><li>Experience building reproducible analytical pipelines or automated workflows</li><li>Good software engineering habits, including Git, documentation and reproducibility</li><li>Ability to work closely with wet-lab scientists and translate scientific requirements into computational workflows</li></ul><p><strong>Nice to Have</strong></p><ul><li>Experience with 384-well or 1536-well plate-based assay data</li><li>lmfit, Pandera, scikit-learn, Biopython or RDKit</li><li>Background in drug discovery, biotech, pharma or CRO environments</li><li>Experience across biophysics, cell biology, enzymology, oncology or immunology</li><li>Experience with high-throughput screening, assay validation or automated lab platforms</li></ul><p><strong>The Candidate</strong></p><p>The ideal candidate will be scientifically fluent and technically hands-on. You may come from a scientific data science, computational biology, bioinformatics, research software engineering or scientific software background.</p><p>You should be comfortable working with complex experimental data, applying statistical rigour and building tools that improve speed, reproducibility and scientific insight across a multidisciplinary team.</p><p></p><img src="https://www.jobg8.com/Tracking.aspx?aP%2fblHlMLSu%2fK49uvsO72Id4g2dEy4Gfr" width="0" height="0" />