Machine Learning Lead

AstraZeneca
Barcelona, Spain
8 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English

Job location

Barcelona, Spain

Tech stack

Computational Biology
Continuous Integration
Information Engineering
Machine Learning
TensorFlow
PyTorch
Multi-Agent Systems
Deep Learning
Machine Learning Operations

Job description

At Alexion, AstraZeneca's Rare Disease unit, you will be the Indication Research team's technical lead for ML engineering as we build an AI platform that transforms indication research for rare diseases into a data-driven and systematic triage process.

Your mission is to co-design and develop the platform's ML components. You will integrate and develop models working on biomedical knowledge graphs, multi-omics and imaging data, and real-world evidence to deliver mechanistic predictions and rank opportunities. Further, you will collaborate and communicate closely with bioinformatics, data engineering and digital infrastructure teams to inform our AI-driven drug development strategy.

What you will do

· Provide technical leadership in ML engineeering, research, and MLOps

· Build, validate, and integrate end-to-end ML capabilities into the Indication Research Platform, including the design, development, training, and optimization of graph ML methods over biomedical knowledge graphs.

· Develop and integrate multi-agent frameworks within the Indication Research Platform.

· Coordinate with bioinformatics, data engineering, and digital infrastructure teams to define and encourage best practices.

Requirements

· PhD in ML/CS/statistics (computational biology experience welcomed).

· Proven record designing deep learning architectures and running rigorous, large-scale experimentation in PyTorch/TensorFlow.

· Fluency in linear algebra, calculus, statistics, probabilistic methods and causal reasoning

· Familiarity with biomedical knowledge graphs, ontology alignment, and graph ML at scale.

· Hands-on experience or collaborative work applying machine learning to omics, imaging data, and RWE.

· Proficient in CI/CD and ML model lifecycle best practices, with experience running GPU workloads in cloud and distributed environments.

Apply for this position