AI Associate Principal - Radioconjugate Discovery

Job Title: AI Associate Principal - Radioconjugate Discovery

Location: Hamilton, Ontario

Onsite 5 days/week

Description:

Fusion Pharmaceuticals, part of the AstraZeneca Group, is redefining precision oncology with next‑generation radioconjugates that deliver powerful alpha‑emitting payloads directly to tumors. Our pipeline spans multiple first‑in‑class programs—backed by a GMP‑compliant, brand new radiopharmaceutical facility in Hamilton, we’re turning groundbreaking science into real‑world impact for patients. Join us at the forefront of radiopharma innovation and be part of turning breakthrough science into meaningful outcomes for patients—come build what’s next with us!

The Role:

The AI Associate Principal - Radioconjugate Discovery will be accountable for designing, building, deploying, and maintaining software and AI-enabled solutions that accelerate Radioconjugate (RC) Discovery. The AI Associate Principal combines software engineering, data engineering, automation, and applied AI to transform complex scientific workflows into scalable, reliable, and user-friendly tools.

This is a hands-on builder role. You will work directly with RC Discovery scientists to find opportunities, rapidly prototype solutions, and use AI-assisted coding to design, build, test, document, deploy, and maintain production-quality analytical tools. You are expected to write and review code, interrogate data, troubleshoot workflows, and iterate with end users, not solely advise, commission work, or provide strategic oversight.

As an embedded technical leader, you will help shape the RC Discovery AI and data science strategy, establish fit-for-purpose engineering practices, mentor colleagues, and deliver measurable value through improved consistency, efficiency, reproducibility, traceability, and scientific decision-making. You will work closely with Data & AI colleagues, data and software engineers, computational scientists, and scientific partners across imaging, DMPK, safety, translational research, and other relevant collaborators. It will also involve collaboration with cloud, cybersecurity, IT operations, legal, privacy, quality, and compliance teams to ensure that solutions are secure, compliant, maintainable, and fit for purpose.

Responsibilities:

• •Hands-on AI-assisted software development: Personally design, write, review, test, debug, deploy, and maintain code using modern AI-assisted development approaches. Apply sound software engineering judgment to validate generated code, manage dependencies, protect data integrity, and ensure solutions are scientifically and technically fit for purpose.
• •Workflow discovery and prioritization: Partner directly with RC Discovery scientists to observe and understand current workflows. Identify recurring difficulties and sources of variability. Prioritize use cases based on scientific value, feasibility, adoption potential, and operational impact.
• •End-to-end solution delivery: Lead the full lifecycle from problem definition and data exploration through prototyping, model or algorithm development, validation, implementation, user acceptance, release, documentation, training, monitoring, and continuous improvement.
• •RC Discovery data and analytics: Develop solutions that integrate, analyze, and visualize structured and unstructured discovery data. Potential applications include biodistribution, imaging, radiochemistry, in vitro and in vivo assay data, immunohistochemistry (IHC), PK/PD and dosimetry-related analyses, automated quality control, scientific reporting, and decision-support workflows.
• •Applied AI and intelligent automation: Leverage AI, machine learning, large language models, statistical methods, and other computational approaches when they provide clear value. Prioritize practical, maintainable, and user-adopted solutions over methodological novelty.
• •Software engineering and platform development: Design and maintain robust software applications, APIs, data pipelines, automation frameworks, dashboards, and scientific platforms that support RC Discovery workflows. Apply modern engineering practices to ensure reliability, maintainability, scalability, and long-term supportability.
• •Consistency and reproducibility: Create standardized and traceable analytical pipelines that reduce manual handling, minimize avoidable errors, improve reproducibility, and promote consistent interpretation and reporting across RC Discovery programs.
• •Data and model quality: Define fit-for-purpose validation approaches, data-quality checks, test cases, acceptance criteria, version control, and performance monitoring. Clearly communicate assumptions, limitations, uncertainty, and appropriate use of outputs.
• •Architecture, security, and compliance: Design solutions with consideration for scalability, maintainability, access controls, information security, data privacy, intellectual property protection, and applicable regulatory and AstraZeneca AI-governance requirements.
• •Technical leadership: Advise on guidelines and innovative methods, set pragmatic technical standards, make build-versus-buy recommendations, and guide project decisions while remaining directly involved in implementation.
• •Collaboration and translation: Translate scientific and business needs into clear technical requirements and convert complex data and model outputs into actionable insights for scientific and non-technical audiences.
• •Capability building: Mentor and coach colleagues in data literacy, responsible AI use, reproducible analytics, AI-assisted coding, and effective adoption of new tools. Develop clear user documentation and training materials.
• •External awareness and innovation: Maintain current knowledge of relevant AI, data science, computational biology, and scientific software trends. Evaluate emerging methods and external collaborations for practical application within RC Discovery.

Qualifications:

• •Bachelor's, Master's, or PhD degree, or equivalent extensive experience, in computer science, mathematics, statistics, engineering, computational science, bioinformatics, cheminformatics, or a related quantitative field.
• •Strong hands-on programming capability, particularly in Python and relevant scientific or data libraries, with the ability to rapidly learn and apply additional languages or platforms as needed.
• •Experience with software-engineering practices including modular design, version control, code review, automated testing, documentation, reproducible environments, issue tracking, and release management.
• •Demonstrated experience designing, developing, validating, deploying, and supporting AI, machine-learning, advanced analytics, or data-science solutions with real-world scientific or business impact.
• •Demonstrated use of AI-assisted coding tools to accelerate development while independently verifying code correctness, scientific validity, security, maintainability, and performance.
• •Experience integrating and analyzing large, complex, heterogeneous datasets and building robust data pipelines, analytical applications, or decision-support tools.
• •Ability to translate ambiguous scientific problems into testable requirements, prototypes, validated solutions, and sustainable user workflows.
• •Strong analytical judgment, attention to data quality, and ability to communicate assumptions, limitations, uncertainty, and validation evidence.
• •Excellent collaboration, consulting, written, and verbal communication skills, with experience influencing technical and non-technical collaborators.
• •Experience leading technical projects, mentoring colleagues, and delivering through multi-functional collaboration while remaining a hands-on individual contributor.

Desirable:

• •Experience in pharmaceutical, biotechnology, life-science, healthcare, or drug-discovery environments.
• •Understanding of radioconjugate or radiopharmaceutical discovery workflows, including one or more of biodistribution, molecular imaging, radiochemistry, in v