Associate Principal Scientist, AI for Predictive Safety
AstraZeneca is hiring an Associate Principal Scientist, AI for Predictive Safety. Level rates it ; you can apply on AstraZeneca.
Level's read on this job
- On Level's scale, this role is Builds AI ●●●●: the job is building AI systems.
- Tools and skills the posting cites include MLOps and computer vision.
- Level classifies it as a lead role.
- Level lists 1,300+ other open roles at AstraZeneca.
- The role was posted in the last few days.
AI in this role
About the team
Predictive AI and Data team is responsible for providing AI and Bioinformatics solutions to the scientists across the spectrum of drug development and discovery in AstraZeneca (both pre-clinical and clinical stages). The primary aim is to find ways to accelerate the drug development process by leveraging existing company data in combination with the most cutting-edge AI approaches in day-to-day scientific work across the company.
Introduction to role
In this role you will lead the next‑generation predictive safety modelling at scale, applying chemoinformatics, bioinformatics and AI/ML to deliver decision-shaping safety insights and cross-functional scientific leadership. Provide scientific leadership for predictive safety modelling, integrating chemical and biological data (e.g., Safety Omics, Cell Painting, NAMs) to inform risk assessment and progression decisions. This is a fully hands-on, computational role with cross-functional influence.
Accountabilities
· Develop, optimise and deploy predictive safety models for small molecules and biologics using chemoinformatics, bioinformatics, computer vision, protein modelling and ML/AI.
· Design and deploy ML/AI models for transcriptomics (bulk and single-cell), proteomics and other omics data to identify toxicity signatures, mechanisms of action and safety biomarkers, including robust normalisation, batch correction and uncertainty quantification.
· Lead the development of machine vision models for Cell Painting, high-content imaging and advanced cell models (e.g., organoids, microphysiological systems), from ideation and proof of concept through to deployment in production in collaboration with R&D IT.
· Apply protein language models and structure prediction methods (e.g., AlphaFold, ESM) to assess safety and developability liabilities of biologics, such as immunogenicity, aggregation, polyreactivity and off-target binding.
· Serve as scientific lead for project teams and influence program strategy.
· Drive innovation and identify strategic modelling opportunities across R&D.
· Lead collaborations with academia, consortia and technology partners.
· Communicate complex modelling concepts to diverse scientific and governance audiences.
Essential Skills/Experience
· PhD (or equivalent years of experience) in mathematics, computer science, engineering, physics, statistics, computational sciences, chemoinformatics, bioinformatics, computational biology, structural biology, computational toxicology or a related field.
· Demonstrated experience in implementing machine learning/AI workflows to automate bioinformatics, cheminformatics or image analysis pipelines, ideally in the Pharma and/or Healthcare space
· Advanced Python programming skills.
· Familiarity with GitHub, CI/CD pipeline, and best DevOps and MLOps practices
· Hands-on familiarity with modern machine learning architectures in at least two of the following areas: chemical structure modelling (e.g., GNNs (graph neural networks), directed message-passing neural network (D-MPNN) and foundation models such as CheMeleon); omics modelling (e.g., transcriptomic foundation models such as scGPT or Geneformer); machine vision (e.g., CNNs, vision transformers and self-supervised models for cellular imaging); and protein modelling (e.g., protein language models such as ESM and structure prediction tools such as AlphaFold).
· Experience analysing and integrating multimodal biological and chemical datasets (e.g., bulk or single-cell transcriptomics, proteomics, high-content imaging and compound structure data), including data QC, normalisation and batch correction.
· Experience with multimodal biological + chemical datasets.
· Proven leadership in delivering impactful modelling work.
· Excellent communication and stakeholder engagement skills.
· Acts as discipline leader and shapes scientific strategy.
· Solves complex problems using scientific judgement.
· Builds strong cross-functional relationships and networks.
· Coaches and mentors others, enhancing team capability.
Desirable Skills/Experience
· Experience with Safety Omics data, and with building machine vision models for Cell Painting, high-content screening, histopathology or other imaging data, including self-supervised and foundation models.
· Background in toxicology, pharmacology or ADMET.
· Experience with cloud computing or workflow automation.
· Track record of publications in top AI conferences or journals in pharmaceutical research (e.g., NeurIPS, ICML, Nature Machine Intelligence, Nature Communications, NEJM AI, etc.)
· Experience supervising scientists or managing collaborations.
Date Posted
16-11月-2026Closing Date
AstraZeneca embraces diversity and equality of opportunity. We are committed to building an inclusive and diverse team representing all backgrounds, with as wide a range of perspectives as possible, and harnessing industry-leading skills. We believe that the more inclusive we are, the better our work will be. We welcome and consider applications to join our team from all qualified candidates, regardless of their characteristics. We comply with all applicable laws and regulations on non-discrimination in employment (and recruitment), as well as work authorization and employment eligibility verification requirements.
How we rate this
Associate Principal Scientist, AI for Predictive Safety at AstraZeneca rates 95 out of 100 for how much of the daily work is AI. That makes it Builds AI (AI Level 4 of 4). The level is about AI in the job, not seniority.
Builds AI. The job is building AI systems.
- ●●●● Builds AI80 to 100
- ●●●○ Works on AI60 to 79
- ●●○○ Uses AI40 to 59
- ●○○○ Little AI0 to 39
Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.
Prepare for this job
Built from this posting and from similar jobs on Level.
Skills and AI tools this role asks for
Questions you could be asked
- How do you monitor a model once it's live, and how do you know it needs retraining?
- Walk me through a computer vision problem you solved, from raw data to a deployed model.
- How would you decide a model or AI system is ready to ship?
- Tell me about a time a model underperformed in production. How did you find out, and what did you change?
Adapt your resume
- List these exact terms on your resume: ML Ops and Computer vision. An applicant tracking system matches the wording, not the idea.
- Attach one line of real, concrete experience to at least one of them. A tool named with nothing behind it rarely survives a human read.
- Lead with what you built, trained or shipped. This role is judged on the AI system itself, not the tools around it.
Get your CV reviewed before you apply
Send your CV and the role you want next. Your review arrives by email within 3 days.
Get new AI jobs (Builds AI ●●●●) by email
One email a week, each job rated for how much AI is in the work. No recruiter spam, unsubscribe in one click.
Free.
Similar roles
Other roles that build AI, at other companies.
STAGE – Ingénieur en développement et démonstration d’une IA de confiance pour drones (H/F) – 6 mois
What kind of AI work fits you?
Answer 12 practical questions in about three minutes. Get a simple profile, the work it points to, and live roles to explore next.
Find my next step