Job Description
Main Activities and Responsibilities
Knowledge Generation
To undertake high quality research & scholarship, including contributing to drafting major grant proposals and/or leading on drafting small grant proposals, and evaluating teaching practice
To contribute to peer-reviewed publications and other outputs, including as lead author
To make a contribution to doctoral student supervision, as appropriate to qualifications and experience
To manage small grants or elements of larger grants, ensuring compliance with good practice in relation to the conduct of research, the ethics policy and other relevant LSHTM policies
To lead the development and operationalisation of NeoShield’s Clinical Decision Support Algorithm (CDSA), including model design, training, validation and preparation for integration into routine clinical workflows
To lead the development and operationalisation of the Ward-Level Outbreak Detection System, including construction of aggregated surveillance models and integration with dashboards and automated alerting tools
To work closely with clinical and laboratory teams to gather operational feedback, understand workflow needs, and adjust both models to maximise usability and clinical relevance
To design and deliver a structured evaluation framework that monitors model performance, accuracy, clinical impact and user experience, and to oversee iterative refinement throughout the grant period
To create and maintain reproducible analytic pipelines, documentation and version-controlled codebases that support transparency, maintenance and scaleup of NeoShield’s digital tools
To produce high-quality research outputs, including peer-reviewed publications, open-source code, technical reports, academic presentations and policy-oriented summaries
To ensure that all machine-learning activities comply with responsible AI/machine-learning principles, including fairness, transparency, safety, and alignment with ethical and regulatory requirements in partner countries
Education
To contribute to the delivery of high quality, inclusive, research-informed teaching and assessment in relation to your specific subject and within the broader area covered by your department and disciplinary field
To contribute to the improvement of the quality of LSHTM’s education, by participating in the development of new and updated learning and teaching materials or approaches
To co-supervise MSc summer projects aligned with NeoShield’s aims and outputs
To support the development of linked PhD studentships, where appropriate
Internal Contribution
To undertake activities that support the Department, Faculty, MRC Unit or LSHTM
To reflect LSHTM’s EDI goals in your work and behaviour
To participate in LSHTM’s PDR process
To actively participate in activities by the AMR Centre, MARCH Centre, and DASH activities, contributing specialist expertise in applied machine learning, digital health and infection modelling
To support internal workshops, cross-centre collaborations, working groups and strategic discussion that advance LSHTM’s capabilities in AI/machine-learning for global health, and to share lessons emerging from NeoShield’s research
External Contribution
To demonstrate good external citizenship by contributing to learned society/conference events, journal and grant reviews
To support the design and delivery of training materials, workshops and job aids for clinicians, laboratory team and Ministry of Health partners on the use, interpretation and safe deployment of NeoShield’s machine-learning tools
To contribute to capacity-building in partner organisations by supporting local teams to operate, evaluate and improve the CDSA and outbreak system after implementation
To represent NeoShield at external meetings, conferences, workshops and stakeholder engagements, demonstrating leadership in applied machine-learning for neonatal care and infection surveillance
To contribute to open-source communities, public repositories and collaborative forums where NeoShield tools and methods could be shared for wider adoption and scale-up
Professional Development and Training
To keep up to date with the latest research/thinking in your academic field and with changes to pedagogic practice within LSHTM and more generally
Where the length and nature of the position permits, to apply for and, if accepted, undertake a doctoral degree (if not already acquired)
To undertake and successfully complete the mandatory training required by LSHTM as appropriate to the role
To remain up to date with advances in machine-learning, digital health systems and infection analytics, participating in relevant meetings, webinars and seminars as required
General
All academic staff are free within the law to question and test received wisdom, and put forward new ideas and controversial or unpopular opinions, to enable LSHTM to engage in research and promote learning to the highest possible standards
All staff at LSHTM are also expected to:
Act at all times in LSHTM’s best interests
Treat staff, students and visitors with courtesy and respect at all times
Comply fully with LSHTM policies, procedures and administrative processes relevant to the role, including when acting as Principal Investigator, accepting academic, managerial, financing and ethical responsibility for a project
Uphold and support LSHTM’s values (as set out in the LSHTM Strategy)
Act as ambassadors for LSHTM when hosting visitors or attending external events
Academic Expectations
All academic roles have a statement of academic expectations attached to each level. Please ensure that these have been read and understood. For further information please refer to the Academic Expectations page
The above list of duties is not exclusive or exhaustive and the role holder will be required to undertake such tasks as may reasonably be expected within the scope and grading of the role
Role descriptions should be regularly reviewed to ensure they are an accurate representation of the role
Person Specification
Essential Criteria
A postgraduate degree, ideally a doctoral degree, in a relevant topic (e.g., machine learning, data science, statistics, computer science, engineering, epidemiology or another relevant quantitative field)
Applied experience in machine-learning, with extensive experience of hands-on model development, testing, validation and deployment using real-world datasets in operational environments (e.g., digital health systems, public health platforms, or other complex production settings such as logistics, finance, energy, mobility, or large-scale consumer or industrial systems). Experience must be beyond classroom or theoretical work
Contributions to written output, preferably peer-reviewed, as expected by the subject area/discipline in terms of types and volume of outputs
Proven ability to work independently, as well as collaboratively as part of a research team, and proven ability to meet research deadlines
Evidence of excellent interpersonal skills, including the ability to communicate effectively both orally and in writing
Evidence of good organizational skills, including effective time management
Experience working with temporal or time-series data
Demonstrated experience in data engineering and ETL workflows required to prepare large, real-world dataset for machine-learning development
Evidence of producing well-documented, version-controlled code (e.g., GitHub/GitLab) and familiarity with best practices in reproducible, transparent machine-learning workflows
Desirable Criteria
Some experience of contributing to research grant applications
Some experience of teaching and assessment
Some experience of supervising and supporting junior researchers and/or research degree students, and non-academic staff
Experience working with healthcare or biological datasets, including routine clinical, laboratory or microbiology data
Experience working within multi-disciplinary research teams, especially across data science, clinical, laboratory, or global health domains
Experience with model interpretability, safety evaluation, or bias assessment in applied machine-learning systems
Experience deploying models or analytics into production environments, including digital applications, dashboards, APIs, or real-time decision-support tools, and working across different compute environments such as cloud-based infrastructure and on-premise local servers
Experience engaging with ethical, regulatory, or governance frameworks related to AI, machine-learning, data protection or responsible innovation in health (e.g., fairness, bias mitigation, accountability, transparency and safety)
Experience working in environments with high autonomy and end-to-end ownership of technical systems, such as start-ups, scale-ups, applied research labs, or small product teams
Deadline: 15 Feb 2026
