Research Fellow / Senior Research Fellow in Software Development for Cancer Digital Twins

Cancer Institute Faculty of Medical Sciences

Job Description

Research Fellow / Senior Research

£

• £ Fellow in Software Development for Cancer Digital Twins

Department: Research Department of Oncology Grade 7: £43,981- £54,019 per annum Grade 8: 56,431 62,903 per annum Salaries are inclusive of London Allowance

Location: UCL Cancer Institute, London

Reports to

Professor Jasmin Fisher

Context

This post is based in Professor Jasmin Fisher’s laboratory at the UCL Cancer Institute. The UCL Cancer Institute is a world-leading centre for cancer research, bringing together more than 400 scientists and clinicians who work collaboratively to understand cancer and translate discoveries into improved diagnostics, treatments and patient outcomes.

We are seeking a highly motivated and talented Senior Research Fellow in Software Development to join an ambitious and multidisciplinary research programme focused on understanding cancer using AI to generate digital tumour twins. This programme aims to transform cancer research and precision oncology by developing a new generation of transparent, interpretable and trustworthy AI technologies that integrate machine learning, mechanistic modelling, formal verification and large-scale biomedical data.

Cancer is a complex, multi-scale disease involving interacting processes across the molecular, cellular, tissue and organ levels. At the same time, advances in genomics, molecular profiling, pathology, imaging and clinical data collection have generated unprecedented volumes of multimodal cancer data. A major challenge is to integrate these diverse data sources into coherent computational frameworks that can generate biological insights, support clinical decision-making and accelerate therapeutic discovery.

The Fisher laboratory addresses this challenge through the development of tumour digital twins, which are executable mechanistic models that capture the biological behaviour of individual tumours and can be used to predict disease progression and treatment response. A central goal of the programme is to develop a novel neurosymbolic AI platform that combine the power of large language models and machine learning with formal reasoning, mechanistic modelling and formal verification to automatically construct and validate transparent, interpretable biologically grounded models directly from large-scale cancer datasets and scientific knowledge.

The successful candidate will play a central role in the design and development of a neurosymbolic AI platform for cancer. They will contribute to the integration and analysis of large-scale multi-omics and clinical cancer datasets, the development and fine-tuning of AI models and the creation of explainable and verifiable computational frameworks for tumour digital twins. Working at the intersection of artificial intelligence, formal methods and cancer research, the postholder will collaborate closely also with Professor Mateja Jamnik and her group in the Department of Computer Science and Technology at University of Cambridge, alongside biologists, and organisations.

The research will contribute to fundamental advances in our understanding of cancer biology while supporting the development of innovative approaches for patient stratification, therapeutic target discovery, treatment optimisation and precision oncology. The successful candidate will have the opportunity to publish in leading journals, present their work at major international conferences and contribute to the development of transformative AI technologies with significant scientific and clinical impact.

This is an exceptional opportunity for an ambitious research software development engineer (RSDE) who is passionate about applying cutting-edge formal verification and AI technologies to challenging realworld problems in biomedicine. The position offers the chance to work at the forefront of trustworthy neurosymbolic AI, formal reasoning, computational biology and cancer systems medicine, within a worldleading research environment committed to scientific excellence and translational impact.

Appointment at Grade 7 and Grade 8 is dependent upon the successful award of a PhD who have not yet been awarded their PhD may be appointed initially at Research Assistant Grade 6B (with progression to Grade 7 and backdated salary adjustment upon submission of the final corrected PhD thesis.

Appointment at Grade 8 is contingent on the candidate’s previous experience.

For more details about the Fisher Lab, please visit: This post is funded for 3 years in the first instance, with a probationary period of 9 months.

Applications should include a CV and a Cover Letter: clinicians computer scientists from partner

. Candidates www.ucl.ac.uk/cancer/fisher-lab In the Cover Letter, please provide evidence of the essential and desirable criteria in the Person Specification part of the Job Description. (By including a Cover Letter, you can leave blank the 'Why you have applied for this role' field in the application form, which is limited in the number of characters it will allow.)

Cancer Institute Faculty of Medical Sciences

Main purpose of the job

The post-holder will contribute to a major new research programme focused on developing trustworthy neurosymbolic AI platform and tumour digital twins to improve our understanding of cancer and support the development of personalised therapeutic strategies. The role will involve the development of computational approaches that combine biological knowledge with advanced AI and formal reasoning methodologies.

Applicants should hold a PhD in Computer Science, Software Engineering, Mathematics, Physics or a related quantitative discipline, with experience in software development for artificial intelligence and data-intensive applications. Strong programming, software engineering and system design skills are essential, together with substantial experience in developing scalable, maintainable and welldocumented software systems. Candidates must have experience with deep learning, large language models (LLMs) and generative AI technologies, as well as the development, integration and deployment of AI-enabled applications.

Applicants should have demonstrable experience in designing, implementing, testing and deploying software platforms that support machine learning and AI workflows, including model integration, API development, distributed systems and cloud-native architectures. Experience with cloud computing platforms and services (e.g., AWS, Azure or Google Cloud), containerisation technologies, continuous integration/continuous deployment (CI/CD) pipelines, automated testing and modern software engineering practices is essential.

Candidates should have experience in developing tools and platforms for the management, curation, integration and analysis of large-scale, heterogeneous datasets, together with familiarity with data governance, reproducible computational workflows and software solutions for AI applications.

Experience with databases, knowledge graphs, semantic technologies and ontology-driven systems would be advantageous.

Experience with formal verification methods is essential, including familiarity with automated theorem proving, program synthesis, symbolic reasoning and formal specification techniques. Knowledge of logical modelling, knowledge representation and neurosymbolic AI approaches is highly desirable.

Applicants should also have experience with the deployment, evaluation and monitoring of large language models, including model optimisation, performance assessment and reliability testing.

Familiarity with model interpretability, explainable AI (XAI) methods and frameworks for understanding model behaviour and ensuring trustworthy AI systems is desirable.

Excellent analytical, problem-solving and communication skills are essential, together with the ability to work independently and collaboratively within a multidisciplinary team of software engineers, AI researchers, computational biologists and clinicians. The successful candidate will be expected to

contribute to the development of a robust and scalable neurosymbolic AI platform for cancer research and digital twins.

Candidates must have excellent written and verbal communication skills, including experience presenting complex scientific concepts to a range of audiences and contributing to high-quality scientific publications. They should demonstrate a strong commitment to the Fisher Lab’s mission and values, together with excellent interpersonal and the to multidisciplinary teams.

skills ability work effectively within

The post-holder will be expected to support other members of the Fisher Lab, collaborate with external academic and clinical partners and contribute to the organisation and smooth running of the laboratory as appropriate.

Duties and responsibilities

The post-holder will be expected to

• Plan, develop and undertake innovative, high-quality research aligned with the objectives of the research programme.
• Lead the software design, development and maintenance of a scalable neurosymbolic AI platform to support the creation and application of cancer digital twins.
• Design, implement and optimise robust software infrastructure that integrates large language models, formal reasoning systems, automated theorem provers and mechanistic cancer models.
• Develop high-quality, reusable and well-documented software components, APIs, libraries and services to support AI-enabled cancer research.
• Build and maintain cloud-based and distributed computing infrastructures for large-scale AI model development, deployment and evaluation.
• Design and implement software pipelines for the ingestion, curation, integration and management of large-scale heterogeneous biomedical, multi-omics and clinical datasets.
• Develop software solutions that support model deployment, monitoring, versioning, validation and reproducibility across the AI platform.
• Implement formal verification, program synthesis and automated reasoning methodologies to support the development of trustworthy and reliable neurosymbolic AI systems.
• Contribute to the development of software tools for model interpretability, explainability, verification and performance assessment.
• Contribute to open-source software releases and research publications.
• Ensure the accuracy, integrity, scalability, security, reproducibility and reliability of all software systems and computational infrastructure, following best practices in software engineering and research computing.

• Establish and maintain software engineering standards, including testing frameworks, code review procedures, version control, continuous integration and continuous deployment (CI/CD) pipelines.
• Collaborate closely with AI researchers, computational biologists, clinicians and external collaborators to translate research requirements into robust software solutions.
• Work with researchers across UCL, partner organisations and international collaborators to support the development and deployment of the neurosymbolic AI platform.
• Independently plan and manage technical work packages, identify solutions to complex engineering challenges, and deliver agreed milestones within project timelines.
• Evaluate emerging technologies, software frameworks and computational approaches relevant to artificial intelligence, formal methods, cloud computing and biomedical data science.
• Maintain accurate, comprehensive and up-to-date technical documentation, software records and development logs in accordance with UCL policies and best practices.
• Support and advise colleagues on software architecture, cloud infrastructure, AI deployment, data engineering and computational workflows.
• Contribute to the preparation of technical reports, software documentation, research papers and other project outputs.
• Contribute to scientific publications, grant applications and funding proposals where appropriate.
• Present technical developments and project outcomes at laboratory meetings, workshops, conferences and other scientific or technical forums.
• Communicate technical concepts, software developments and project progress effectively to both specialist and non-specialist audiences.
• Participate in laboratory meetings, project meetings, seminars, workshops and professional development activities relevant to the role.
• Assist in the supervision, training and mentoring of students, research assistants and junior developers where appropriate.
• Contribute to a collaborative, inclusive and supportive research and software development culture within the Fisher Lab.
• Participate in laboratory, departmental and institute activities commensurate with the grade of the post.
• Assist with project coordination, software release management, infrastructure management and administrative responsibilities as required.
• Adhere to all UCL policies and procedures, including those relating to Equality, Diversity and Inclusion, information governance, data protection, cybersecurity, research integrity, data management, health and safety, and fire regulations.
• Undertake any other duties commensurate with the grade and responsibilities of the post as reasonably required by the Principal Investigator.

General

• Follow and actively promote the UCL Ways of Working.
• Takes responsibility to carry out duties in a way that embodies UCL's environmental and social sustainability values, actively supporting within the remit of their role.
• Carry out any other duties within the scope, spirit and purpose of the job as requested by the line manager.
• This job description may be reviewed and be subject to amendment in consultation with the post holder.

Person Specification

Note to job applicant: copy and paste the following criteria into your “Statement in support of your application” and describe underneath each criteria how you meet it, giving examples. You will be scored on how you meet each criteria.

Essential Criteria

Qualifications, experience and knowledge

PhD in Computer Science, Software Engineering, Mathematics, Physics or Machine Learning Proven track record of high-quality research and/or software development, evidenced by publications in peer-reviewed journals, conferences, opensource contributions, or significant software projects.

Excellent programming and software engineering skills, with substantial experience in designing, developing, testing and maintaining robust, scalable and reproducible software systems.

Demonstrable experience in modern software development practices, including version control (e.g., Git), automated testing, software documentation, code review, continuous integration and continuous deployment (CI/CD).

Experience in designing and implementing distributed, cloud-based or high-performance computing solutions for data-intensive applications.

Experience with cloud computing platforms and services (e.g., AWS, Microsoft Azure or Google Cloud).

Experience developing software systems and infrastructure for machine learning, deep learning models, large language models (LLMs) and generative AI applications.

Experience integrating, deploying and evaluating AI models within production or research software environments.

UCL's Sustainability Strategy, policies and objectives Application Application

Application & Interview

Application & Interview Application

Application & Interview

Application & Interview

Application & Interview

Extensive experience with formal verification methods, automated Application & Interview theorem proving, program synthesis, symbolic reasoning and related computational logic techniques.

Excellent written and verbal communication skills, with the ability to communicate complex technical concepts to both specialist and nonspecialist audiences.

Ability to work effectively within a multidisciplinary and collaborative research environment.

Skills and Abilities

Excellent software design, computational, analytical and problem-solving skills.

Strong knowledge of software architecture, software lifecycle management and best practices in software engineering.

Ability to develop maintainable, scalable and well-documented software solutions.

Strong organisational skills, including the maintenance of accurate, traceable and reproducible code, documentation and technical records.

Experience implementing reproducible computational workflows and research software practices.

Strong knowledge of formal methods, model checking, software verification frameworks and program synthesis methods Experience developing APIs, microservices and containerised applications Experience developing open-source software and supporting communitydriven software projects.

Ability to work independently, take initiative and drive technical development projects to completion.

Excellent attention to detail and commitment to quality, reliability and robustness in software development.

Strong forward-planning, project management and time-management skills, with the ability to prioritise competing demands and deliver against deadlines.

Ability to critically evaluate research findings and contribute innovative ideas to ongoing projects.

Ability to collaborate effectively with researchers, software engineers and domain experts from diverse scientific and technical backgrounds.

Commitment to developing software that supports reproducible, trustworthy and transparent AI systems.

UCL Ways of Working

Taking pride in delivering an excellent service to colleagues, students, partners and the wider community.

Actively seeking solutions to any bullying, harassment and discriminatory behaviour in teams

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview Application Application

Application & Interview

Application & Interview

Application & Interview Desirable Criteria

Experience with neurosymbolic AI systems and the integration of machine learning with symbolic reasoning approaches.

Knowledge of logic and mechanistic model approaches Experience with explainable AI (XAI), model interpretability and trustworthy

AI methodologies.

Experience with research computing infrastructure, workflow management systems and large-scale data platforms Experience applying AI and software engineering methods to biological, biomedical or healthcare applications.

Knowledge of cancer biology, systems biology or computational biology Experience with multi-omics, clinical or biomedical data integration.

Experience contributing to collaborative research proposals, grant applications or large-scale research projects.

Experience supervising, mentoring or training students, research assistants or junior developers.

Experience working within interdisciplinary teams spanning artificial intelligence, computer science and life sciences.

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview

Application & Interview