Sr.) Principal Oligo Data Scientist

Job description

Site Name: USA - Massachusetts - Cambridge

Posted Date:
Jul 22 2025

The Oligotherapy Principal Data Scientist role is embedded in and directly supports the Oligo Sciences team whose broad remit is the design, characterization, and early development of oligonucleotide therapies. Oligo data scientists will serve a dual purpose of co-developing a data capture & analysis platform with oligo sciences experts and translating their needs broadly across GSK to build methods/models/capabilities that fulfil them.

• Co-design and implement a target tractability system for oligo-guided therapeutic mechanisms such as RNA degradation/interference, and up/down modulation of alternative splicing, poly-adenylation, A>
  
  I edit, etc.
• Co-develop a target/complex engagement model that combines target sequence, secondary+ tertiary structure, and oligo chemistry to drive binding assay designs for both high-throughput screening and low-latency optimization.
• Collaborate effectively with renowned GSK experts in genetics, genomics, computational bio & chem, structural biology and medicinal chemistry, artificial intelligence / machine learning, and digital technologies to build the datasets, tools, models, and infrastructure necessary for oligo design & development.

• PhD degree in computational life science (bio/med/chem/stats/informatics) with minimum of 1 year published work.
• Minimum of 2 years’ experience Post Doctoral or Pharmaceutical Industry experience.
• Minimum of 1 year experience with genomic data infrastructure for either public or private collections (e.g. ENCODE, TCGA, Dep Map, GTEx, cell Xgene, UK biobank.
• Minimum of 1 year experience with Cheminformatic or structural modelling of drug-target binding for small or large molecules validated by real qSAR assays.
• On-site presence of 2-3 days per week on average required.

• Demonstrated cross-functional communication, matrixed collaboration, both team and thought leadership.
• Performed target identification or tractability/prioritization for RNA-modulating approaches or RNA-targeted modalities.
• Participated in high-throughput or high-content screening for hits followed by low-latency iterations for lead optimization.
• Developed analytic tools & data pipelines for processing & querying large batches of disease/perturbation/control samples.
• Biology research focus on either coding or non-coding RNA and its post-transcriptional regulation in various eukaryotic cells/tissues.
• Chemistry research focus on oligonucleotide modifications: either synthetic sugars/backbones, or natural nucleobase variants.
• Mastery of statistical learning or predictive modelling with signals and noise in empirical datasets: either observational or perturbational.
• Mastery of predictive analytics and modern data stack: principal developer on a codebase in Python/R/Julia/C++/Java/Rust, or considerable and consistent contributions to an open-source project, or Top
  10 placement in life-science-themed competitions on Kaggle/Top Coder/DREAM challenge.
• Familiarity with Bayesian statistics and machine learning (ML & DL) with prudent use of suitable methods as projects progress.
• Familiarity with genetic mutations’ impacts on both coding and non-coding RNA sequences and their associated binding proteins, especially in regulating alternative splicing, poly-adenylation, and RNA chemical modifications like methylation or editing.
• Knowledge of 2o and 3o structure and computational/experimental techniques (e.g. Chemical probing, NMR, CryoEM) to determine folding dynamics of eukaryotic RNAs in complex with chaperone RNP and RBPs.