5 of 5 White-Box Testing Jobs in the UK

Helping drive quality from conception to finished product Developing detailed, comprehensive, and well-structured test plans and test cases Applying and maintaining automated testing processes for our products Contributing to the growth of our regression packs and ensuring we maintain a high level of automated test coverage Identifying … software QA methodologies, tools and processes Experience with Playwright Programming skills in JavaScript Strong SQL skills Hands-on experience with both white-box and black-box testing Good spoken and written English A keen eye for detail and a commitment to excellence ...

components. Collaborating deeply with Software Engineers throughout the entire development lifecycle, from initial requirements capture to final deployment. Designing, building, and maintaining automated testing frameworks to increase delivery velocity while ensuring system correctness. Performing rigorous manual and automated testing (including unit, integration, and system-level tests … supports continuous improvement and seamless client handovers. Desirable Skills Strong command of common testing methodologies (e.g., Black-box, White-box, Regression, and Exploratory testing). Proven experience with automated testing tools and frameworks relevant to modern operating systems ...

work of frontier AI labs, government agencies, and national security institutes. Our research spans fundamental research using black-box and white-box approaches to understand and steer AI systems, to building and advancing safety evaluations which better understand and quantify risks in AI. … building AI evaluations or benchmarks, alongside a strong ability to reason about construct validity and mitigate confounds. Expertise in red-teaming, adversarial testing, jailbreaking, indirect prompt injection, and assessing the robustness of model safeguards. Strong foundational skills in experimental design, statistical analysis, and uncertainty quantification, including Bayesian methods. ...

capable model attempting to cause harm is an empirical question that remains largely untested. The Control Red Team at AISI is stress‐testing control monitors (including from GDM and Anthropic) – finding attacks that beat monitors and attempting to design experiments to measure real-world risk. We’re based … complex research projects involving substantial engineering. This includes black-box work (API-based evaluations and attacks) and ideally some white-box work (e.g. fine‐tuning open-weight models). Strong software engineering and ML experience: writing clean, documented, reusable code for machine learning experiments ...

that generate the evidence, writing arguments, and arguing them out with the rest of the team. We intend to publish this work. 2. Testing: Running evaluations of frontier labs' monitors, and reporting the implications . Turning our research into concrete assessments of real systems: threat modelling … complex research projects involving substantial engineering. This includes black-box work (API-based evaluations and attacks) and ideally some white-box work (e.g. fine-tuning open-weight models). Strong software engineering and ML experience: writing clean, documented, reusable code for machine learning experiments ...