Senior AI/ML Engineer - Test Automation | RAG | Self-Healing | LLM

CodeNinja is a next-generation technology consulting firm specialising in AI-powered transformation, enterprise software delivery, and Quality Engineering. Headquartered in the Gulf region and operating across the MENA, South Asia, and global markets, CodeNinja partners with Tier-1 banks, government entities, and large enterprises to design, build, and run mission-critical technology programs.

With deep expertise in QA transformation, test automation, DevOps modernisation, and AI/ML engineering, CodeNinja's teams combine global delivery standards with in-market contextual knowledge — ensuring outcomes that are compliant, scalable, and commercially aligned with client objectives.

For the Client's Test Management Enablement & Automation engagement, CodeNinja brings a dedicated 12-person specialist team spanning Test Management, Automation Engineering, AI/ML, and Performance Testing — all governed under a structured 20-week program delivery framework.

The AI/ML Engineer builds the RAG pipeline for BRD-to-test-plan generation, develops self-healing locator models, implements risk-based regression optimisation, and operates within the client's AI governance framework. This is a pioneering role at the cutting edge of intelligent test automation.

•        Design and build the Retrieval-Augmented Generation (RAG) pipeline to analyse BRD documents and generate test plans and test designs.

•        Develop self-healing element identification models for UI automation, targeting >85% recovery rate.

•        Implement risk-based regression optimisation algorithms to prioritise test execution by change impact.

•        Build defect clustering and root cause pattern recognition capabilities.

•        Ensure all AI models operate within the client's AI governance framework: PII-free training data, synthetic data only, human-in-the-loop validation.

•        Version-control all AI models with rollback capability and maintain comprehensive audit trails.

•        Produce explainable AI outputs with confidence scores and reasoning traceability.

•        Collaborate with the client's CISD and AI governance teams on model approvals and compute/GPU access.