Senior Scientific Data Scientist

Company/ Role Overview

Arctoris is seeking a Senior Scientific Data Scientist / Pipeline Engineer to design, implement, and maintain the analytical pipelines that power our data-driven drug discovery platform.

This role is ideal for a scientist-turned-coder or data scientist with strong Python skills, statistical modelling expertise, and experience with bioassay data - paired with solid software engineering discipline.  

If you thrive at the intersection of biology, data, and scientific automation, enjoy partnering with wet-lab teams, and want to build robust tools that accelerate therapeutic discovery, this is the ideal opportunity.

Main Responsibilties

Scientific Analysis & Pipeline Development

• Build, maintain, and extend Python-based analytical pipelines for diverse bioassay datasets (biochemical, biophysics, and cell-based assays).
  
  

• Implement robust statistical and modelling workflows, including:
  
  

  • dose–response modelling and curve fitting (e.g., 4PL, mechanistic models)
    
    

  • QC and normalisation frameworks
    
    

  • plate-level statistics and data validation
    
    

• Translate scientist workflows into reproducible, automated analysis pipelines.
  
  

Data Engineering & Workflow Structuring

• Design structured ETL/ELT processes for experimental data ingestion, curation, and transformation.
  
  

• Develop clean, maintainable, well-tested Python codebases using solid software engineering principles.
  
  

• Use lightweight workflow tools (e.g., Snakemake, Luigi, or similar) to organise multi-step scientific analyses.
  
  

Scientific Collaboration & Communication

• Partner closely with wet-lab scientists to:
  
  

  • understand assay logic and experimental design
    
    

  • identify improvements to data structures and analysis readiness
    
    

  • streamline file preparation and data handover
    
    

• Provide input on experimental interpretation where it helps clarify analytical or QC decisions.
  
  

Infrastructure & Tooling (Nice-to-Have)

• Support backend integration with cloud storage or databases (AWS S3, PostgreSQL, etc.).
  
  

• Contribute to internal scientific tooling, dashboards, or lightweight GUIs (optional).
  
  

• Assist with continuing evolution of scientific data architecture.

Qualifications and Experience

Scientific & Analytical

• Strong experience analysing plate-based bioassay data (384- or 1536-well formats).
  
  

• Proficiency in Python for scientific computing, including NumPy, Pandas, SciPy, curve fitting libraries such as lmfit, and visualisation libraries such as Matplotlib/Seaborn. Experience with scikit-learn for exploratory analysis (e.g., PCA, clustering), data validation tools (e.g., Pandera), and scientific libraries such as Biopython or RDKit is highly beneficial.
  
  

• Solid understanding of statistical modelling, curve fitting, and QC in experimental biology.
  
  

• Ability to work across multiple scientific domains and adapt to varied assay formats.
  
  

Software Engineering

• Proficient in:
  
  

  • modular design and code organisation
    
    

  • testing (PyTest/Unittest)
    
    

  • version control (Git)
    
    

  • clear documentation and reproducibility
    
    

• Experience developing end-to-end data or analysis pipelines.
  
  

Collaboration & Communication

• Able to work fluidly across scientific teams and translate scientific needs into computational workflows.
  
  

• Clear and structured communicator; capable of articulating analytical choices and modelling approaches.
  
  

• Strong problem-solving mindset.

Desirable Skills

• Experience with lightweight workflow managers (e.g., Snakemake, Luigi).
  
  

• Familiarity with AWS or cloud storage systems.
  
  

• Database experience (PostgreSQL/MySQL) and data modelling.
  
  

• Background in biophysics, cell biology, enzymology, or other relevant scientific domains.
  
  

• Exposure to containerisation (Docker) or CI/CD (GitHub Actions). 

• Ability to develop simple user-facing interfaces (e.g., Streamlit).
  
  

About us

Arctoris is a technology-enabled drug discovery services company headquartered in Oxford. We combine automated wet lab experimentation, proprietary analytical pipelines, and deep scientific expertise to accelerate the design and optimisation of new therapeutics. Our proprietary Ulysses automation platform and data infrastructure enable the generation of reproducible, high-quality datasets at scale, forming the foundation for AI-driven discovery capabilities across oncology, immunology, and neurodegeneration.

We operate at the intersection of biology, robotics, and data science, building systems that transform how scientists generate and interpret experimental data. Joining Arctoris means contributing to a multidisciplinary environment where innovation in data architecture, analytical tooling, and computational pipelines directly advances the creation of life-changing medicines.

---