Design and implement the unified AI Quality strategy and SOP, scaling controls by risk tier (Tier 1–3)
Define and own success metrics, risk tiering, acceptance criteria, and operating thresholds for AI solutions
Lead the development of golden/adversarial test suites (prompt injection, misuse, safety, bias, functional automation)
Oversee the creation and maintenance of schema-level UI/API tests, agent contracts, and observability instrumentation
Own the org-wide evaluation harnesses (e.g., promptfoo, TruLens, Ragas), CI gating, and red-team playbooks
Manage independent spot checks, factsheets, registry entries, and evidence for governance and audit
Collaborate with Product Owners, Developers, SRE/Observability, and Governance to ensure compliance and operational excellence
Drive continuous improvement in fairness, explainability, safety, security, and operational SLOs
Mentor and grow the AI Quality team, including onboarding and coaching junior engineers

Experience leading or building quality engineering or testing programs (AI/ML experience is a plus, but not required)
Ability to design and implement test strategies, automation frameworks, and quality standards
Excellent communication and leadership skills; ability to work cross-functionally and influence stakeholders
Experience with LLM, RAG, agentic, or classic ML systems
Familiarity with test automation frameworks, CI/CD pipelines, and evaluation tools (promptfoo, TruLens, Ragas)
Knowledge of fairness, explainability, safety, and security standards (e.g., OWASP Top 10, MITRE ATLAS, Fairlearn, AIF360)
Experience with data integrity, lineage, and observability (OpenTelemetry, New Relic, OpenLineage)
Familiarity with AI infrastructure, orchestration, data integrity, deployments, and model registry practices
Knowledge of international standards and regulatory frameworks for Responsible AI
Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, or related field, or equivalent experience

AI Quality Lead

Key skills