expertise needed Filters

Requires hands-on machine-learning engineering: training, adapting, evaluating or serving models

Requires knowledge of statistical methods and analysis

Requires deep understanding of the problem domain

Requires skill in designing test suites, benchmarks, adversarial scenarios and rating or annotation protocols to judge model behaviour, including building ground-truth sets and deciding what counts as a pass.

Requires access to and understanding of a neural network's internals: gradients, activations, attention weights and layers. Narrower than ml-engineering, which would keep training, adaptation and operation.

Requires security expertise for threat analysis and mitigation

Requires knowledge of privacy-enhancing methods and privacy threat modelling: disclosure and re-identification risk, privacy budgets, and the utility cost of protection.

Requires general programming and system design skills

Requires organisational governance and audit practice: running review or oversight processes, keeping accountable records, and writing documentation that an auditor or regulator relies on.

Requires understanding of the legal and regulatory requirements that apply to the system

Requires safety engineering principles and practices

Requires knowledge of how people oversee, rely on and interact with AI systems: designing human review workflows, managing reviewer workload and fatigue, and communicating model confidence and limits to users.

Requires skills in building and maintaining data pipelines, storage, versioning, lineage and logging infrastructure.

Requires skills in stakeholder communication and engagement

Requires knowledge of ethical principles and frameworks

Requires understanding of causal relationships and inference

Requires cryptographic knowledge for privacy-preserving techniques

Requires linguistic knowledge for language-based techniques