Associate AI Quality Engineer

About Foodics

Foodics, established in 2014, is a leading restaurant management ecosystem and payment technology provider. Headquartered in Riyadh, the company operates offices across five countries and serves customers and partners in over 35 countries globally, having processed more than 6 billion orders. Foodics is recognized as a rapidly evolving SaaS company within the MENA region, supported by significant funding rounds.

Role Overview

The Associate AI Quality Engineer will contribute to building internal AI systems utilized daily by engineers. This full-time role, based in Riyadh Province, specifically Riyadh, involves developing agents for test generation and maintenance, pipelines for failure triage, tooling for code review and debugging, and evaluation infrastructure for AI features. This is a builder's role focused on writing production code and owning systems within CI, with performance measured by the adoption of work by engineers.

Key Responsibilities

• Implement test automation across the technology stack, including backend API and contract testing, service-level and integration coverage, and robust data setup.
• Develop frontend web E2E and component-level coverage using Playwright, including visual and RTL regression, and fast suites for merge gating.
• Ensure mobile native and cross-platform coverage with Appium or Maestro, manage device-farm strategy, and test offline, sync behavior, and payment-peripheral paths on real hardware.
• Manage shared fixtures, environment and test-data, parallelization, and CI pipelines to ensure meaningful build failures.
• Conduct performance and load testing.
• Develop AI layers for test generation from specifications, code, and production traffic, focusing on maintenance.
• Implement failure triage systems to classify build failures (bugs, flakes, environment issues, test rot) before human intervention.
• Create self-healing locators and suite health tooling, including flake detection, quarantine, and coverage-gap analysis.
• Build evaluation infrastructure for AI features across products, encompassing datasets, scoring, and regression detection for prompt or model changes.
• Focus on evaluation specific to the market, including Arabic and English behavior, RTL interfaces, and region-specific POS, tax, and payment rules.
• Develop agentic AI for pipeline tasks such as reading diffs, running relevant suites, reproducing failures, proposing fixes, and opening PRs.
• Create agents that manage end-to-end quality workflows, including exploratory testing, coverage-gap hunting, and release-risk assessment.
• Design orchestration systems that manage multi-step planning, tool use, retries, state and memory across steps, sandboxed execution, and multi-agent handoffs.
• Integrate AI systems with existing infrastructure such as CI, Jira, observability, and MCP-style tool interfaces.
• Exercise judgment to determine when a plain pipeline is more effective than an agent and advocate for such solutions.

Technical Grounding

Candidates should possess current knowledge and be able to discuss the practical application of the following areas:

• Test Automation: Framework design and layering, test pyramid concepts and limitations, flake economics, parallel execution, mobile and cross-browser testing, and CI/CD gating. Familiarity with Playwright, Appium, and Maestro frameworks is relevant.
• Agentic AI: Orchestration and tool use, multi-step planning, memory and state management, sandboxed execution, multi-agent patterns, MCP and similar tool-integration standards, and associated costs.
• Context Engineering: Retrieval strategies, chunking, reranking, caching, and managing long-context behavior, including degradation.
• Evaluation: Offline and online evaluations, LLM-as-judge methodologies and failure modes, human-in-the-loop review, statistical significance on small samples, and regression gates in CI.
• Reliability: Structured output, guardrails, fallback and retry design, and handling non-determinism in critical systems.
• Operations: Tracing and observability for LLM systems, prompt and version management, latency and cost budgeting, model routing, and understanding when fine-tuning or distillation is more effective than prompt engineering.

Company Culture and Benefits

Foodics offers an inclusive and diverse culture that supports innovation and flexibility, including in-office and hybrid work arrangements. The company provides competitive compensation packages, which may include bonuses and potential for shares. Personal development is prioritized through regular training and an annual learning stipend. Employees join a team of over 30 nationalities working in 14 countries, with opportunities for autonomy, mentoring, and challenging goals.