Senior Manager of AI Safety and Validation Engineering

Client of Discovered MENA

Discover the Opportunity We are hiring a Senior Manager of AI Safety and Validation Engineering to join a leading bank in their Group Business Services division. This is primarily a technical practitioner role focused on the design and implementation of technical measures to ensure the reliability and security of advanced AI solutions. You will bridge the gap between cutting edge AI development and rigorous risk standards while serving as a technical liaison to second line risk functions Discover the Role As a Senior Manager of AI Safety and Validation Engineering, you will lead the creation of evaluation frameworks for both predictive Machine Learning and Generative AI. You will be responsible for defining standardised monitoring protocols and automated guardrails. Working as an individual contributor, you will provide hands on execution support to various product teams to ensure all deployments meet high performance and compliance standards. Discover the Responsibilities • Define standardised evaluation rubrics and scoring systems for system performance and safety across various AI archetypes including RAG and agentic workflows. • Design comprehensive test cases covering deterministic logic and adversarial scenarios to stress test AI outputs. • Implement automated evaluators such as LLM-as-a-judge and targeted small language models Deploy explainability techniques like Shapley Values and Integrated Gradients to ensure model transparency and unfair bias detection in lending and fraud models. • Partner with platform teams to build telemetry pipelines that capture embeddings and inputs while maintaining strict data privacy standards. • Establish golden signals such as hallucination rates and semantic similarity to trigger automated circuit breakers when performance thresholds are breached. • Analyse guardrail violations to identify emerging attack patterns and integrate human-in- the-loop corrections into model refinement cycles. • Translate technical telemetry into actionable model health reports for second-line risk functions Work with specialist software vendors to bring advanced safety capabilities into the internal AI ecosystem.