Software Quality Assurance Engineer - AI Agents

Lucidya; Saudi Arabia; On-site; SAR 200,000 - 300,000; Full time

Job summary

A leading AI solutions provider in Saudi Arabia is seeking a QA Engineer to define and uphold quality standards for AI agents. This role involves extensive collaboration, manual and automated testing of workflows and integrations, and requires a Bachelor’s degree in a relevant field. Ideal candidates will have experience in API testing and automation, particularly with Playwright, and strong communication skills. The culture emphasizes collaboration and continuous improvement, providing opportunities for significant impact within a new business unit in the AI sector.

Benefits

Opportunity to work in a high-impact role

Collaborative and ownership-driven culture

Qualifications

• 2–5 years of experience in QA engineering (manual + automation).
• Programming/scripting experience in Python, JavaScript, or Java.
• Comfortable working with shifting priorities.

Responsibilities

• Partner with teams to define acceptance criteria and quality benchmarks.
• Perform manual and exploratory testing for various workflows.
• Design, build, and maintain automated test suites.

Skills

Strong QA Fundamentals

Manual Testing

Exploratory Testing

Defect Analysis

Strong Communication

Adaptability

Education

Bachelor’s degree in Computer Science or related field

Tools

Playwright

Jira

Git

CI tools (Jenkins, GitHub Actions)

JMeter

Job description

What You’ll Do (Key Responsibilities)

AI Agent Quality & Test Strategy
Partner with product, AI, data, and engineering teams early (“shift-left”) to define acceptance criteria, test scenarios, and quality benchmarks for AI agents.
Participate in requirement discussions to assess testability, risks, and edge cases specific to AI-driven behavior.
Help define what “good quality” means for AI agents (reliability, fallback behavior, latency, error handling, consistency).

Manual & Exploratory Testing

Execute manual and exploratory testing for AI agent workflows, integrations, and end-to-end scenarios.
Validate agent behavior across happy paths, edge cases, failure states, and real-world enterprise use cases.
Conduct regression testing across multiple agents, channels, and environments.
Validate cross-browser and cross-device behavior for agent-facing UIs (web and mobile where applicable).

Automation & CI/CD

Design, build, and maintain automated test suites (UI, API, end-to-end), with Playwright preferred.
Extend automation frameworks to support agent workflows, conversational paths, and backend orchestration.
Integrate automated tests into CI/CD pipelines and collaborate with DevOps to ensure reliable releases.

API, Backend & Non-Functional Testing

Perform deep API and backend workflow testing to ensure AI agents interact correctly with internal and external systems.
Support performance, load, and reliability testing—especially for concurrent agent usage and peak enterprise loads.
Assist in security testing initiatives for AI agent integrations and data flows.
Support test data strategies across environments, including realistic AI scenarios.

Quality Governance & Reporting

Log, track, and triage defects; collaborate closely with engineers and AI teams to reproduce and resolve issues.
Provide release readiness assessments, risk analysis, and defect trend reporting for agent deployments.
Advocate for usability, accessibility, reliability, and enterprise-grade quality across the AI Agents portfolio.

Continuous Improvement

Contribute to QA best practices, standards, and documentation tailored to AI agent systems.
Help evolve testing approaches for AI-driven products (e.g., exploratory heuristics, scenario-based testing).
Stay current with modern QA trends, including AI-assisted testing, automation improvements, and cloud testing tools.

What You Must Have (Non-Negotiables)

Strong QA Fundamentals
Solid manual and exploratory testing skills, strong defect analysis, and the ability to identify edge cases and risks.
Practical Automation Experience
Hands‑on experience building, maintaining, and troubleshooting automated tests (Playwright preferred).
API & Backend Testing Competency
Ability to test APIs and validate backend flows thoroughly.
High Adaptability
Comfortable working across manual, automation, performance/security, requirement discussions, and shifting priorities.
Strong Communication & Ownership
Clear communicator, proactive collaborator, takes ownership of quality, and willing to participate in occasional rotational weekend support.

Skills & Qualifications

Bachelor’s degree in Computer Science, Engineering, or a related field.
2–5 years of experience in QA engineering (manual + automation).
Programming/scripting experience in Python, JavaScript, or Java.
Automation experience with Playwright is a strong plus.
Proven experience in API testing (required).
Experience with Git, CI tools (Jenkins, GitHub Actions, GitLab CI), and defect tracking tools like Jira.
Exposure to performance/load/security testing tools (JMeter, Locust, OWASP ZAP) is a plus.
ISTQB or equivalent certification is a plus.
Strong English communication skills.
Strong organisational and time‑management skills across multiple projects.
Ability to work independently with moderate supervision.
Comfortable giving and receiving structured feedback.
Willingness to join infrequent rotational weekend support for critical issues.
Adaptable to changing product priorities and organisational structures (pods/squads or QA‑as‑a‑service).

Why Join Lucidya - AI Agents

Be part of building a brand‑new AI Agents business unit from the ground up.
High‑impact role shaping how enterprise AI quality is defined and measured.
Exposure to modern AI‑driven systems, complex integrations, and advanced QA tooling.
Collaborative, ownership‑driven culture focused on learning and continuous improvement.
Opportunity to influence quality standards for AI products used by leading enterprises across MENA.