Senior Scientist: Data Pipelines and AI for Lab Analytics

F. Hoffmann-La Roche AG; Basel; On-site; CHF 140,000 - 210,000; Full time

Job summary

Roche Basel invites researchers and engineers to join a team modernizing analytical workflows across NMR, MS, LC/GC-MS, XRPD and open-access data. You will turn data from instruments into reliable products and first-line decisions, while upholding FAIR data and governance standards.

You will build pipelines, ensure data quality and lineage, migrate legacy scripts, and develop bounded ML/AI for routine classification with human review.

Qualifications

• Master's or PhD in analytical chemistry or related field.
• Strong Python and SQL skills with Linux/HPC experience.
• Hands-on familiarity with analytical laboratory data and systems (NMR, MS, XRPD).
• Demonstrated ML/AI and software‑engineering discipline: testing, version control, monitoring.

Responsibilities

• Own, document and prioritize the modernization roadmap for NMR, MS, LC/GC-MS, XRPD and open-access analytical workflows.
• Build and maintain pipelines, APIs and connectors linking instruments, software, ELN/LIMS and reporting tools.
• Implement metadata capture, data-quality checks, lineage, observability, recovery procedures and archival aligned with FAIR.
• Migrate critical scripts onto supported pipeline platforms and retire legacy components with ownership.
• Develop bound ML/AI for routine analytical classification, anomaly detection and first-line interpretation with human review.
• Own analytical AI products end to end, including DiPLab or agent-assisted interpretation, in CsCoE/RDT environments.
• Support adoption through onboarding, training and workflow documentation.

Skills

Python

SQL

Data engineering

ML/AI

Education

Master’s degree or PhD in analytical chemistry, scientific computing, data engineering, cheminformatics or related field

Tools

Linux/HPC

APIs

ELN/LIMS

Workflow orchestration

Job description

Roche Basel invites researchers and engineers to join a team modernizing analytical workflows across NMR, MS, LC/GC-MS, XRPD and open-access data. You will turn data from instruments into reliable products and first-line decisions, while upholding FAIR data and governance standards.

You will build pipelines, ensure data quality and lineage, migrate legacy scripts, and develop bounded ML/AI for routine classification with human review.