Senior QA Engineer (AI-First)
Inspect AR by Augment IT
/job-details/13302
**About us**
At Augment IT we build Inspect AR, a platform that changes how inspections and maintenance are done in industries where reliability is critical. Inspect AR combines digital workflows, artificial intelligence and augmented reality to help field teams run checklists, carry out tasks, work fully offline on site, and produce detailed reports. Leading infrastructure operators use it every day. When our product fails, real inspections stall, so quality is central to what we do.
We are a small, senior team. Everyone owns their area, decisions happen quickly, and your work has a visible effect on the product and on our customers.
**The role**
**We are looking for an experienced Senior QA Engineer (AI-First)**
to own quality across our web, iOS and Android platforms and to build our QA practice around AI from day one. You will set up and lead the QA and validation process from the start and ensure that the software does what it is intended for (validation). You will decide how we test, which parts AI agents and tools handle, and when a release is ready.
This is not a role where AI is an occasional helper. We expect you to work intensively with AI every day. You will design and run AI-based workflows that generate, run, maintain and analyse our tests across all platforms, so that a small team can reach coverage and speed that would normally take a much larger one. You will also remain the human quality gate who decides what the AI output is worth.
**Location**
Skopje, Macedonia
on-premise / hybrid possible
**What you’ll do**
- Own and lead QA for the web and mobile versions of the product, including strategy, planning and execution.
- Design and establish AI-based testing workflows across web, iOS, Android and Realwear, covering test design, automation, execution, triage and reporting.
- Closely align with the CTO to setup the technical infrastructure to run automations reliably.
- Use AI agents and coding assistants to generate and maintain automated test suites for functional, smoke, regression and performance testing.
- Turn requirements, user stories, tickets and customer issues into test cases with AI support, and review them for correctness and relevance.
- Ensure that the system is validated - it does not only function technically, but according to the specifications it produces the correct output and behaviour.
- Use AI for exploratory testing, edge-case discovery, synthetic and realistic test data generation, and visual and UI regression checks.
- Build AI-assisted failure analysis that clusters flaky or failing tests, analyses logs and screenshots, and proposes root causes and fixes.
- Integrate AI-driven steps into our CI/CD pipelines so tests are created, updated and assessed continuously rather than by hand.
- Maintain shared prompts, agent configurations and workflow documentation so the whole team can reuse and extend your AI tooling.
- Measure what the AI workflows actually deliver, including coverage gained, time saved and false positives, and drop what doesn’t add value.
- Define how we test the AI features in our own product, including non-deterministic outputs, model changes and computer vision results.
- Make sure AI tools are used safely with customer data, in line with our security and data protection requirements.
- Give a release sign-off for every version, backed by a concise report on test coverage, results and open risks.
- Reproduce customer-reported issues and give engineers precise, reliable reproduction steps.
- Work closely with developers and product in the team’s regular rituals, and raise risks early.
- Mentor teammates in AI-assisted testing and spread good practices across the team.
**What you bring**
- BSc in Computer Science, Software Engineering, or a related technical field.
- 4+ years of professional QA experience, including significant hands-on work in test automation.
- Proven, intensive daily use of AI in QA work, with concrete examples of AI-based testing workflows you have built and run in practice.
- Strong willingness to learn and adapt latest developments in AI to automate testing and validation of the software.
- Hands-on experience with AI coding assistants and agents (for example Claude Code, GitHub Copilot or Cursor) and with agent-driven automation for browsers and mobile apps (for example Playwright MCP or similar MCP-based tooling).
- Strong prompt and workflow design skills, and the judgement to verify, correct and reject AI output instead of trusting it blindly.
- Solid programming skills in at least one modern language (for example C#, TypeScript/JavaScript, Python, or Swift), with the ability to write and review clean, maintainable test code, whether you or an AI wrote it.
- A proven record of building test plans and automation frameworks from scratch for web and mobile applications.
- Strong knowledge of modern automation and reporting tools (for example Playwright, Cypress, Appium, XCUITest, or similar) and of CI/CD integration.
- Solid understanding of the product development and release process: Git branching, tagging, versioning, hotfix flows, and deployments, along with distributing and installing test builds via TestFlight, Google Play testing tracks, and direct Android APK installs.
- A solid grasp of testing best practices: the test pyramid, risk-based testing, and how to keep test suites stable and maintainable.
- Awareness of the data protection and security considerations of using AI tools in an enterprise setting.
- Fluent written and spoken English.
**How you work**
- **AI-first**
. For every task, your first question is how AI can do it faster or better, and your second is how you will verify the result.
- **Independent and dependable**
. You take ownership, meet deadlines, and flag delays before anyone has to ask.
- **Precise**
. You care about detail, and your bug reports, test cases and status updates are clear and to the point.
- **Pragmatic**
. You focus testing effort where the risk is highest instead of aiming for 100% of everything, and you use AI where it pays off, not for its own sake.
- **Curious**
. You follow how AI tooling develops and try new approaches quickly.
- **A team player**
. You question assumptions constructively, ask the right questions, and help raise the standard for everyone.
- **Proactive**
. You find problems and opportunities before they become urgent.
**Nice to have**
- Experience testing AI/ML features or evaluating LLM and computer vision outputs.
- Experience building custom AI agents, MCP servers or tool integrations for testing.
- Experience testing AR, 3D or computer vision applications.
- Experience with offline-first or sync-heavy mobile apps.
- Performance or load testing experience (for example k6 or JMeter).
- Experience in enterprise B2B or regulated industries.
**What we offer**
- A key role with real ownership in a small, high-trust team.
- The freedom and budget to shape an AI-first QA practice from scratch.
- Work on technology that is both interesting and genuinely useful: AR, AI and field-ready mobile software used by major enterprise customers.
- Direct influence on the product, our processes and our tooling.
- Competitive salary
- 5 days of education per year
- Benefits that are valid for all employees: Private health insurance, lunch, ability to work in our office in Skopje or from home (please note that Augment IT doesn’t support the full remote / work-from-home mode and you may be asked to come to the office regularly if needed).
At Augment IT we build Inspect AR, a platform that changes how inspections and maintenance are done in industries where reliability is critical. Inspect AR combines digital workflows, artificial intelligence and augmented reality to help field teams run checklists, carry out tasks, work fully offline on site, and produce detailed reports. Leading infrastructure operators use it every day. When our product fails, real inspections stall, so quality is central to what we do.
We are a small, senior team. Everyone owns their area, decisions happen quickly, and your work has a visible effect on the product and on our customers.
**The role**
**We are looking for an experienced Senior QA Engineer (AI-First)**
to own quality across our web, iOS and Android platforms and to build our QA practice around AI from day one. You will set up and lead the QA and validation process from the start and ensure that the software does what it is intended for (validation). You will decide how we test, which parts AI agents and tools handle, and when a release is ready.
This is not a role where AI is an occasional helper. We expect you to work intensively with AI every day. You will design and run AI-based workflows that generate, run, maintain and analyse our tests across all platforms, so that a small team can reach coverage and speed that would normally take a much larger one. You will also remain the human quality gate who decides what the AI output is worth.
**Location**
Skopje, Macedonia
on-premise / hybrid possible
**What you’ll do**
- Own and lead QA for the web and mobile versions of the product, including strategy, planning and execution.
- Design and establish AI-based testing workflows across web, iOS, Android and Realwear, covering test design, automation, execution, triage and reporting.
- Closely align with the CTO to setup the technical infrastructure to run automations reliably.
- Use AI agents and coding assistants to generate and maintain automated test suites for functional, smoke, regression and performance testing.
- Turn requirements, user stories, tickets and customer issues into test cases with AI support, and review them for correctness and relevance.
- Ensure that the system is validated - it does not only function technically, but according to the specifications it produces the correct output and behaviour.
- Use AI for exploratory testing, edge-case discovery, synthetic and realistic test data generation, and visual and UI regression checks.
- Build AI-assisted failure analysis that clusters flaky or failing tests, analyses logs and screenshots, and proposes root causes and fixes.
- Integrate AI-driven steps into our CI/CD pipelines so tests are created, updated and assessed continuously rather than by hand.
- Maintain shared prompts, agent configurations and workflow documentation so the whole team can reuse and extend your AI tooling.
- Measure what the AI workflows actually deliver, including coverage gained, time saved and false positives, and drop what doesn’t add value.
- Define how we test the AI features in our own product, including non-deterministic outputs, model changes and computer vision results.
- Make sure AI tools are used safely with customer data, in line with our security and data protection requirements.
- Give a release sign-off for every version, backed by a concise report on test coverage, results and open risks.
- Reproduce customer-reported issues and give engineers precise, reliable reproduction steps.
- Work closely with developers and product in the team’s regular rituals, and raise risks early.
- Mentor teammates in AI-assisted testing and spread good practices across the team.
**What you bring**
- BSc in Computer Science, Software Engineering, or a related technical field.
- 4+ years of professional QA experience, including significant hands-on work in test automation.
- Proven, intensive daily use of AI in QA work, with concrete examples of AI-based testing workflows you have built and run in practice.
- Strong willingness to learn and adapt latest developments in AI to automate testing and validation of the software.
- Hands-on experience with AI coding assistants and agents (for example Claude Code, GitHub Copilot or Cursor) and with agent-driven automation for browsers and mobile apps (for example Playwright MCP or similar MCP-based tooling).
- Strong prompt and workflow design skills, and the judgement to verify, correct and reject AI output instead of trusting it blindly.
- Solid programming skills in at least one modern language (for example C#, TypeScript/JavaScript, Python, or Swift), with the ability to write and review clean, maintainable test code, whether you or an AI wrote it.
- A proven record of building test plans and automation frameworks from scratch for web and mobile applications.
- Strong knowledge of modern automation and reporting tools (for example Playwright, Cypress, Appium, XCUITest, or similar) and of CI/CD integration.
- Solid understanding of the product development and release process: Git branching, tagging, versioning, hotfix flows, and deployments, along with distributing and installing test builds via TestFlight, Google Play testing tracks, and direct Android APK installs.
- A solid grasp of testing best practices: the test pyramid, risk-based testing, and how to keep test suites stable and maintainable.
- Awareness of the data protection and security considerations of using AI tools in an enterprise setting.
- Fluent written and spoken English.
**How you work**
- **AI-first**
. For every task, your first question is how AI can do it faster or better, and your second is how you will verify the result.
- **Independent and dependable**
. You take ownership, meet deadlines, and flag delays before anyone has to ask.
- **Precise**
. You care about detail, and your bug reports, test cases and status updates are clear and to the point.
- **Pragmatic**
. You focus testing effort where the risk is highest instead of aiming for 100% of everything, and you use AI where it pays off, not for its own sake.
- **Curious**
. You follow how AI tooling develops and try new approaches quickly.
- **A team player**
. You question assumptions constructively, ask the right questions, and help raise the standard for everyone.
- **Proactive**
. You find problems and opportunities before they become urgent.
**Nice to have**
- Experience testing AI/ML features or evaluating LLM and computer vision outputs.
- Experience building custom AI agents, MCP servers or tool integrations for testing.
- Experience testing AR, 3D or computer vision applications.
- Experience with offline-first or sync-heavy mobile apps.
- Performance or load testing experience (for example k6 or JMeter).
- Experience in enterprise B2B or regulated industries.
**What we offer**
- A key role with real ownership in a small, high-trust team.
- The freedom and budget to shape an AI-first QA practice from scratch.
- Work on technology that is both interesting and genuinely useful: AR, AI and field-ready mobile software used by major enterprise customers.
- Direct influence on the product, our processes and our tooling.
- Competitive salary
- 5 days of education per year
- Benefits that are valid for all employees: Private health insurance, lunch, ability to work in our office in Skopje or from home (please note that Augment IT doesn’t support the full remote / work-from-home mode and you may be asked to come to the office regularly if needed).
