Associate Director – AI Bioinformatics Full-time

Associate Director of AI Bioinformatics

Are you ready to turn clinical transcriptomics and AI into decisions that change patient outcomes? Do you want to build production-scale platforms that scientists across the company rely on every day to accelerate the path from discovery to medicines? This role combines brand new machine learning and translational science. It allows global teams to unlock insights from complex data and make bold, informed choices.

As Associate Director of AI Bioinformatics, you will partner with scientists and AI researchers to design, deploy, and scale models that predict risk, segment patients, and power high-throughput screening. Your work will shape the platforms that underpin research across therapeutic areas, connecting rigorous methods with real-world impact. You will champion a production-first approach, ensuring the infrastructure and tooling required to move rapidly from exploration to value in the hands of decision-makers.

Accountabilities:

• Clinical Transcriptomics ML: Design, build, and deploy machine learning models for large-scale analysis of clinical transcriptomics data that drive decisions in development and patient care.
• Risk Prediction and Segmentation: Create models that predict the risk of clinical events and enable robust patient segmentation, and apply AI to high-throughput compound screening to prioritize candidates faster.
• Novel Methods and Methodological Rigor: Apply a range of data science methodologies and develop novel solutions when off-the-shelf techniques do not fit, balancing innovation with statistical robustness and interpretability.
• Collaborator Engagement and Communication: Build and manage effective relationships across scientific and operational teams; clearly communicate results, uncertainties, and limitations to invent solutions and influence direction.
• Global Collaboration: Work effectively across several timezones with AI research teams in China, India, and Europe, clarifying model requirements and evaluating approaches to deliver reliable solutions at scale.
• Production-First Delivery: Champion a production-first attitude and ensure the necessary infrastructure and platforms are in place to scale exploratory research to production-grade capabilities.
• Platform and Tooling Improvement: Contribute to a hard-working team continuously improving machine learning development environments, platforms, and tooling to increase speed, quality, and reproducibility.
• Secure and Compliant AI: Collaborate with Cyber Security and Data Privacy to secure the computing environment without obstructing end-user productivity, maintaining trust and compliance.

Essential Skills/Experience:

• Proven experience designing and deploying machine learning models for large-scale clinical transcriptomics data.
• Hands-on expertise building models to predict risk of clinical events, enable patient segmentation, and support high-throughput compound screening.
• Ability to apply a range of data science methodologies and develop novel data science solutions where off-the-shelf methodologies do not fit.
• Strong collaborator engagement skills and the ability to clearly and objectively communicate results, including uncertainties and limitations, to build solutions.
• Experience working effectively across several timezones with AI research teams in China, India, and Europe, communicating requirements and evaluating available solutions.
• Demonstrated commitment to a production-first attitude to scale exploratory research to production, with the necessary infrastructure and platforms in place.
• Track record of contributing to continuous improvement of machine learning development environments, platforms, and tooling.
• Experience collaborating with internal governance and compliance functions such as Cyber Security and Data Privacy to secure computing environments without obstructing productivity.

Desirable Skills/Experience:

• Advanced degree in bioinformatics, computational biology, computer science, statistics, or a related field.
• Deep expertise with transcriptomics modalities (e.g., bulk RNA-seq, single-cell RNA-seq), feature engineering, and biological interpretation.
• Proficiency in Python and modern ML frameworks (e.g., PyTorch, TensorFlow), and experience with model deployment, MLOps, and cloud platforms.
• Strong background in statistical modeling for clinical outcomes, survival analysis, and uncertainty quantification.
• Familiarity with healthcare data standards, GxP principles, and privacy-preserving analytics; experience in pharma or biotech R&D environments.
• Demonstrated leadership in cross-functional settings, including mentoring, influencing without authority, and driving alignment across diverse collaborators.
• Experience with scalable computing (e.g., GPUs, distributed training), data pipelines, and reproducible research practices.

Why AstraZeneca:

Here, curiosity meets courage and software meets science. You will work shoulder to shoulder with researchers, data scientists, and engineers, using brand new technology and rich datasets to help transform complex biology into actionable insight. We bring unexpected teams into the same room to unleash bold thinking, and we value kindness alongside ambition so you can stretch yourself while being supported. Your contribution directly advances medicines for people with serious conditions, with room to learn, grow, and, when great science comes alive, see your work shared with the world.

Call to Action:

Step into a role where your engineering leadership shapes tools that accelerate discovery—send your CV and help build the systems that move science faster to patients!