Senior Scientific Software Engineer (Fullstack)
Role details
Job location
Tech stack
Job description
A healthier future. It's what drives us to innovate. To continuously advance science and ensure everyone has access to the healthcare they need today and for generations to come. Creating a world where we all have more time with the people we love. That's what makes us Roche.
Advances in AI, data, and computational sciences are transforming drug discovery and development. Roche's Research and Early Development organisations at Genentech (gRED) and Pharma (pRED) have demonstrated how these technologies accelerate R&D, leveraging data and novel computational models to drive impact. Seamless data sharing and access to models across gRED and pRED are essential to maximising these opportunities. The new Computational Sciences Center of Excellence (CoE) is a strategic, unified group whose goal is to harness this transformative power of data and Artificial Intelligence (AI) to assist our scientists in both pRED and gRED to deliver more innovative and transformative medicines for patients worldwide.
The Analytics and Workflows group within the Center of Excellence (CoE) is dedicated to turning complex data into actionable insights that advance drug discovery and development. We leverage cutting-edge high-throughput technologies and foundational multimodal machine learning models to analyze large-scale chemical and biological data, enabling deeper understanding of molecular behavior and the identification of novel therapeutic opportunities. Despite advances in these fields, however, transforming raw data and computational models into meaningful insights remains a key challenge. In this role, you'll work at the intersection of data science, medicinal chemistry, and engineering to build innovative analytical tools that bridge the gap between data generation and interpretation, helping unlock new avenues for scientific discovery and impact., We are seeking a Senior Scientific Software Engineer (Fullstack) to design and build interactive tools for small-molecule drug discovery, with a particular focus on chemical data, molecular design workflows, and model interpretability. You will shape the technical and product direction of platforms that enable medicinal and computational chemists to explore data, test hypotheses, and design better drugs. This role is fullstack, with a strong emphasis on scientific data visualization, workflow design, and integration with computational pipelines. Success will be measured not only by technical delivery, but by the impact on how scientists design and evaluate small-molecule candidates. Your work will include:
- Partnering directly with medicinal chemists, cheminformaticians, and AI scientists to understand real-world molecular design and analysis workflows, including ambiguous or evolving needs.
- Designing and building end-to-end platforms-spanning front-end interfaces, backend services, and data integrations-that enable scientists to run analyses, explore data, and interpret model outputs.
- Leading the development of intuitive, extensible user experiences for complex scientific workflows, with a focus on interactive visualization, usability, and scientific fidelity.
- Architecting and implementing APIs, data models, and services that support scalable, data-intensive applications, including integration with computational pipelines and machine learning systems.
- Evaluating and applying emerging technologies (including AI-assisted development tools) to accelerate iteration, while exploring new approaches to scientific data visualization and user interface design that improve how scientists interact with complex datasets.
- Collaborating across distributed scientific, engineering, and design teams to take ideas from early exploration through production-ready applications, with shared ownership of outcomes and impact.
Requirements
- A Ph.D. in an engineering, physical, or quantitative discipline with 2+ years of experience, or a BS/MS with 5+ years of relevant industry experience.
- Proven track record of designing and building modern web applications across the full stack, including front-end development with TypeScript frameworks (e.g., React, Vue, or Svelte) and backend systems in Python (e.g., FastAPI, Flask) or similar frameworks.
- Expertise in creating interactive, data-rich visualizations using web-based libraries and technologies such as D3.js, Vega-Lite, Plotly, WebGL, or WebGPU, with an emphasis on enabling exploration of complex scientific datasets.
- Experience designing and implementing APIs, data services, and application architectures that support interactive, data-intensive scientific workflows, with attention to performance, scalability, and maintainability.
- Proficiency in leveraging modern AI-assisted and agentic coding practices, with sound judgment about correctness, reproducibility, guardrails, and maintainability in scientific software.
- Curious, eager to grow new skills, and excited to explore emerging technologies while collaborating across diverse, multidisciplinary teams.
- Preference will be given to candidates who are comfortable reasoning about chemical structures and molecular design workflows, including core chemoinformatics concepts (e.g., fingerprints, descriptors, similarity metrics, molecular embeddings), and able to engage productively with medicinal, computational, and machine learning scientists.
- Ability to work effectively with complex datasets in scientific contexts using Python- or R-based tools, including exploring data, developing analyses, and translating results into intuitive, user-facing tools and visualizations.
- Fluency working with data pipelines, cloud infrastructure, and distributed systems (e.g., handling large-scale chemical or biological datasets, integrating with ML model outputs, or orchestrating workflows).