AI/ML Engineer - Phenomics

Role Summary

AI/ML Engineer - Phenomics at GSK. This role is based at multiple sites (USA: California – San Francisco; Cambridge, MA; Seattle; Pennsylvania – Upper Providence; UK: Stevenage; UK: London; Germany: Heidelberg). We’re seeking AI/ML engineers with a track record of developing and validating state-of-the-art ML models to solve real-world scientific problems in healthcare. You will join the AI/ML Phenomics Team to apply cutting-edge ML/AI methods to generate insights from multi-modal high-content data, ranging from spatial transcriptomics of proprietary patient cohorts to high-dimensional imaging and multi-omics readouts from high-throughput genetic and chemical perturbation screens in vitro cellular systems.

Responsibilities

• Carry out product-driven research on novel machine learning methods to analyze terabytes of internal multi-modal high-content data.
• Design approaches to deconvolve real biological signals from confounding effects that are inherent in high-throughput biological data.
• Leverage internal high performance computing cluster and cloud compute to train and productionize our models at scale.
• Work closely with domain experts on cross-disciplinary teams to generate actionable insights that impact target identification, hit identification, and safety testing.
• Contribute to our developing codebase with well-tested, production-ready code.

Qualifications

• Required: PhD or master's in computer science, engineering, applied mathematics, machine learning, or equivalent practical experience.
• Required: 2+ years of experience in cell imaging.
• Required: 2+ years of experience in machine learning and software engineering best practices.
• Required: 2+ years of experience with working in a collaborative CI/CD software development environment, including use of git.
• Required: 2+ years of experience with developing, implementing, and training deep learning models with PyTorch, TensorFlow, or other deep learning frameworks.
• Preferred: Experience working with high-content imaging and diverse multi-omics.
• Preferred: Knowledge in disease biology, molecular biology, and biochemistry.
• Preferred: Track record of writing software in a team in industrial environments or open-source projects.
• Preferred: Track record of projects or peer-reviewed publications at the intersection of machine learning and life sciences.
• Preferred: Mentality of commit early and often, metrics before models, and shipping high quality production code.

Education

• PhD or master's in computer science, engineering, applied mathematics, machine learning, or equivalent practical experience.