Principal Scientist, Genomics Analytics Engineer

GSK•Upper Providence, PA

1d•Hybrid

About The Position

Within GSK R&D Translational Sciences (TSci), the Genomic Technologies team integrates deep and broad expertise in computational, statistical and data-driven methods to enable best-in-class analytical insight and interpretation of genetics and genomics data, impacting GSK R&D portfolio and pipeline decisions. We value collaborative and cross-disciplinary working, partnering closely with translational scientists, portfolio teams, as well as GSK’s AI/ML and platform scientists. We emphasise biological and statistical rigour alongside delivery-focused engineering, analysis reproducibility, and data traceability. This role emphasises end‑to‑end ownership of analytical systems, combining scientific excellence with strong, production‑grade engineering practices to deliver capabilities that can be reliably used across programmes. We create a place where people can grow, be their best, be safe, and feel welcome, valued and included.

Requirements

Strong programming skills (Python required)
Demonstrated experience writing maintainable, production‑quality code, including: modular design, testing, version control
Knowledge of genetic, genomic, epigenomic, or experimental/functional genomic data, and of relevant methods for data analysis and interpretation.
Hands‑on experience building, running, and maintaining data or analytics pipelines using a workflow orchestration framework (e.g. Nextflow, Airflow, Dagster, Prefect, Snakemake) and willingness to adapt to new and emerging technology.
Candidates are not expected to have designed large‑scale platforms but should be comfortable owning pipelines end‑to‑end.
Ability to work independently and take ownership of deliverables

Nice To Haves

Experience working in cross‑functional scientific or R&D teams
Practical experience implementing or operationalising machine‑learning models end‑to‑end (data preparation, training, evaluation, iteration)
Experience deploying or operationalising ML models
Experience working in cloud-based Trusted Research Environments
Deep understanding of statistical genomics/genetics methodology

Responsibilities

Design and implement maintainable analytics and ML pipelines for genomics and multi‑omics data
Implement state-of-the-art tools for dynamically analysing, interpreting, and visualizing genetic and genomic data.
Translate scientific and domain requirements into reliable, testable software systems
Own workflows from prototype through to usable, shareable capability
Apply machine‑learning methods to answer biological questions where appropriate, with an emphasis on robustness, interpretability, and reproducibility
Contribute engineering best practices within a scientific environment (testing, code structure, documentation)
Act as a technical bridge between genomics scientists and AI/ML or platform teams
Contribute to a culture of innovation, quality, and willingness to learn and improve