Associate AI Quality Engineer

About Foodics

Foodics, established in 2014, is a leading restaurant management ecosystem and payment technology provider headquartered in Riyadh, with offices across five countries. The company is recognized as a rapidly evolving SaaS company in the MENA region, having processed over 6 billion orders and secured $170 million in SaaS funding.

Role Overview

Foodics is seeking an Associate AI Quality Engineer for a full-time position in Riyadh. This role is focused on developing internal AI systems used daily by engineers. The successful candidate will write production code, own systems in CI, and be measured by the adoption of shipped solutions.

Key Responsibilities

• Implement test automation across the stack, including API and contract testing for backend, web E2E and component-level coverage with Playwright for frontend, and native/cross-platform coverage with Appium or Maestro for mobile.
• Develop and maintain shared fixtures, environment and test-data management, parallelization, and CI pipelines.
• Conduct performance and load testing.
• Design and implement AI-driven test generation from specifications, code, and production traffic, focusing on long-term maintenance.
• Develop failure triage systems to classify build failures (real bug, flake, environment, test rot) before human intervention.
• Build self-healing locators and suite health tooling, including flake detection, quarantine, and coverage-gap analysis.
• Establish evaluation infrastructure for AI features across products, encompassing datasets, scoring, and regression detection for prompt/model changes.
• Focus evaluation specifically on market needs, including Arabic and English behavior, RTL interfaces, and region-specific POS, tax, and payment rules.
• Develop agentic AI for pipelines to perform 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, release-risk assessment, and escalation to human intervention when necessary.
• Implement orchestration that handles load, multi-step planning, tool use, retries, state and memory management, sandboxed execution, multi-agent handoffs, and clear boundaries between agentic and deterministic steps.
• Integrate AI systems with existing stack components such as CI, Jira, observability, and MCP-style tool interfaces.

Required Skills and Experience

• Demonstrated experience shipping production software, with recent hands-on experience in LLM-backed systems used by real users.
• Strong proficiency in Python; comfort with at least one of .NET, Java, or TypeScript. Experience with tested, maintained code beyond notebooks.
• Proven depth in automation across multiple surfaces, having owned a suite that gates releases on both backend and a UI (web or mobile), with the ability to explain stability maintenance.
• Practical experience building evaluation systems and quantitatively measuring system improvement.
• Practical depth with modern LLM toolkit: prompting, structured output, tool use, retrieval, agentic AI orchestration, and understanding of trade-offs.
• Credible testing fundamentals, including test design, automation frameworks, and CI/CD familiarity.
• A focus on adoption, measuring work by its utility to other engineers rather than by demos.

Candidate Profile

Candidates should possess a current understanding of how this work is executed and be able to articulate this knowledge effectively. This includes expertise in test automation (framework design, test pyramid, flake economics, parallel execution, mobile/cross-browser realities, CI/CD gating), agentic AI (orchestration, multi-step planning, memory/state, sandboxed execution, multi-agent patterns, tool integration standards), context engineering (retrieval strategy, chunking, reranking, caching, long-context behavior), evaluation (offline/online evaluations, LLM-as-judge, human-in-the-loop review, statistical significance, regression gates), reliability (structured output, guardrails, fallback/retry design, handling non-determinism), and operations (tracing/observability for LLM systems, prompt/version management, latency/cost budgeting, model routing, fine-tuning/distillation). Frameworks such as Playwright, Appium, and Maestro are relevant.

Benefits

Foodics offers an inclusive and diverse culture that supports innovation and flexible work setups. The company provides competitive compensation packages, including bonuses and potential for shares. Emphasis is placed on personal development through regular training and an annual learning stipend. Employees join a team of over 30 nationalities working in 14 countries and benefit from autonomy, mentoring, and challenging goals.