7 of 7 Black-Box Testing Jobs in London

clearance.Key ResponsibilitiesDesign, develop, and maintain C++ software for mission-critical defence systems.Apply DO-178 principles and ensure compliance with safety standards.Perform black-box/system-level testing and verification activities.Collaborate with multi-disciplinary teams to integrate software into complex systems.Support configuration management … experience in C++ (modern standards: C++11/14/17/20).Knowledge of DO-178 processes and safety-critical development.Experience with black-box testing, verification, and requirements traceability.Familiarity with configuration management and build tools (Git, Jenkins, CMake).Understanding of coding standards (e.g., MISRA ...

loop oversight and auditability, so it is explainable rather than a black box. Set the bar. Set the standards for security, testing, deployment, monitoring and documentation, manage selected vendors, build the engineering culture, and mentor the junior data engineer. WHAT WE ARE LOOKING FOR A strong … platforms that serve real users and business-critical decisions. Strong programming fundamentals in Python, TypeScript and SQL at expert working level, covering testing, performance and maintainability, with the judgement to review others' code and hold a high-quality bar. Confidence building robust REST APIs, working with relational databases ...

Assume a critical role in defining the future of a globally recognized firm and have a direct and significant effect in a realm tailored for top achievers in site reliability. As a Lead Site Reliability ...

risks, and directly inform the 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 … designing and 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.Deep ...

confidence intervals and hypothesis testing, power analysis, experimental design, causal inference, and Bayesian modeling. Experience designing evaluation methodologies - including black-box and counterfactual approaches - and the test datasets behind them, with good judgment on realism and validity limits. Practical familiarity with evaluating AI systems … into testable criteria. First-hand experience with how modern agentic AI systems are built and their behavior emerges Experience with explainability for black-box systems (surrogate modeling, behavioral analysis, etc) This role isn’t for you if... You've only worked in academic or research settings ...

capable model attempting to cause harm is an empirical question that remains largely untested. The Control Red Team at the company 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. … 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 ...

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 … design, build and run ML experiments on frontier models, and to work autonomously on 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 ...