Senior AI Bioinformatics Scientist

Are you ready to turn large-scale transcriptomics into models that shape the future of cell therapy and patient outcomes? Do you want to partner with world-class scientists to build AI solutions that move from exploratory research to production at scale? This role puts you at the heart of translating omics data into insights that matter for patients and programs.You will join a high-energy team that fuses data, AI and cutting-edge science to advance therapies across complex diseases. Your work will power predictive models for clinical risk, patient segmentation and high-throughput screening, while helping to evolve the platforms and environments that underpin our research. You will see your ideas progress from notebook to production, directly informing decisions and unlocking the next wave of breakthroughs.Accountabilities:- Impactful ML for Cell Therapy: Design, deploy and maintain machine learning models for large-scale clinical transcriptomics in the cell therapy domain, focusing on real-world impact and operational reliability.- Clinical Risk and Segmentation Modeling: Build models to predict clinical events and segment patient populations, enabling better trial design, prioritization and treatment strategies.- High-Throughput Screening Analytics: Create scalable models and pipelines that accelerate compound screening and ranking, increasing discovery velocity and decision quality.- Methodological Innovation: Apply a broad toolkit of data science methods and develop novel approaches when off-the-shelf techniques fall short, ensuring robust, explainable results.- Production-First MLOps: Champion a production mindset from day one; establish the infrastructure, CI/CD, observability and data pipelines required to scale from exploratory analysis to production services.- Platform Evolution: Contribute to continuous improvements in machine learning environments, platforms and tooling to raise developer productivity, reproducibility and model performance.- Stakeholder Partnership: Build trusted relationships across scientific, clinical and product teams; clearly communicate findings, uncertainties and limitations to shape the right solutions.- Secure-by-Design Collaboration: Work closely with Cyber Security and Data Privacy to maintain a secure, compliant computing environment that preserves end-user productivity.- Delivery Excellence: Ensure code quality, documentation and reproducibility standards; drive rigorous validation and monitoring to sustain model value over time.Essential Skills/Experience:- Collaborate with scientists from across the company to understand their challenges and work with them to build the platform that underpins their research.- Take responsibility for designing, and deploying machine learning models for a large-scale analysis of clinical transcriptomics data in Cell Therapy domain- Design and build machine learning models for transcriptomics data to predict the risk of clinical events, patient segmentation, or for high-throughput compound screening- Apply a range of data science methodologies, developing novel data science solutions where off-the-shelf methodologies do not fit- Build and manage effective relationships with stakeholders to ensure utilization and value of information resources and services. Clearly and objectively communicate results, as well as their associated uncertainties and limitations to shape solutions- Champion a “production first attitude” to ensure the necessary infrastructure and platforms are available to scale exploratory research to production.- Be a part of a hard-working team, continuously improving AstraZeneca’s Machine Learning development environments, platforms, and tooling.- Work closely and collaboratively with internal governance and compliance functions such as Cyber Security and Data Privacy to secure the computing environment without obstructing end-user productivity.Desirable Skills/Experience:- Advanced degree in computational biology, bioinformatics, computer science, statistics or related field, or equivalent industry experience- Strong proficiency in Python and/or R, and experience with ML frameworks such as scikit-learn, TensorFlow or PyTorch- Hands-on experience with bulk and single-cell RNA-seq, including preprocessing, normalization, QC and batch correction- Familiarity with clinical data structures and time-to-event modeling, including survival analysis and risk prediction- Experience with model interpretability and uncertainty quantification approaches- Practical MLOps skills: containers (Docker), orchestration (Kubernetes), experiment tracking (MLflow), CI/CD and monitoring- Cloud experience on Azure, AWS or GCP, including scalable data engineering pipelines- Experience analyzing high-throughput screening datasets and integrating multi-omics- Knowledge of data privacy, security and compliance principles in healthcare and research settings- Track record of impactful cross-functional collabo