Job Summary
Role Title AI Engineer — Test Automation (Senior) Function Quality Engineering / Digital Assurance Experience 8–12 years overall, with 3+ years applying AI/ML or LLMs to engineering workflows Location Offshore ROLE OVERVIEW We are looking for a Senior AI Engineer to join an active, large-scale test automation program and raise its ceiling with AI. You will work alongside automation engineers, SDETs and client QA stakeholders to introduce LLM- and agent-based capabilities into the way tests are designed, generated, maintained and triaged — and, equally, to build the new automation frameworks that make those capabilities usable at scale. This is a hands-on engineering role, not an advisory one. You will ship working tooling into live delivery, prove its value with measurable outcomes, and bring the wider automation team along with you. KEY RESPONSIBILITIES Agentic & LLM-based test generation. Design and build LLM-powered capabilities that generate test cases, test scripts and test data from requirements, user stories, API contracts, designs and existing application behaviour. Framework development. Architect and implement new automation frameworks from the ground up — reusable, framework-agnostic layers for web, API, mobile and data pipelines — with AI capabilities designed in rather than bolted on. Autonomous agents. Build agentic workflows that explore applications, propose coverage, self-heal broken locators and assertions, and keep suites current as the product changes. Integration. Integrate AI tooling into existing suites (Selenium, Playwright, Cypress, Appium, REST Assured, Karate) and CI/CD pipelines so that generation, execution and maintenance run as part of normal delivery. Analytics & triage. Apply ML and LLM techniques to failure triage, flaky-test detection, duplicate-defect clustering and risk-based test selection, reducing manual analysis effort per cycle. Quality of AI output. Define prompts, grounding strategies, retrieval patterns and evaluation harnesses so AI-generated test assets are accurate, deterministic enough to trust, and measurably better than the baseline. Engineering rigour. Deploy and operate models and AI services responsibly — versioning, cost control, observability, data handling and client security and compliance requirements. Enablement. Mentor automation engineers and SDETs on AI-assisted practices, run working sessions and demos, and contribute reusable accelerators and documentation back to the practice. Stakeholder engagement. Work directly with client QA leads, product owners and architects to shape the AI roadmap for the program and report progress against agreed metrics. REQUIRED SKILLS & EXPERIENCE 8–12 years in software engineering, test automation or AI/ML engineering, with at least 3 years building AI/LLM-enabled solutions in production or live delivery. Strong programming ability in Python and/or Java or TypeScript, with clean, tested, reviewable code as a habit. Demonstrable experience with LLM application development: prompt engineering, function/tool calling, RAG, vector stores, embeddings, and at least one agent framework (LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, MCP-based agents or equivalent). Proven track record of designing and building automation frameworks from scratch — architecture, abstraction layers, reporting, test data management, parallel execution. Hands-on depth in at least two of: Playwright, Selenium, Cypress, Appium, API automation, performance or data-quality automation. Solid CI/CD and DevOps practice: Git, Jenkins or GitHub Actions or Azure DevOps, Docker, artifact and environment management. Experience evaluating AI output quality — building eval sets, scoring, regression-testing prompts and models rather than relying on impressions. Ability to work inside an existing program: read someone else's framework, respect delivery timelines, and introduce change incrementally without destabilising live suites. PREFER
Key Responsibilities
Role Title AI Engineer — Test Automation (Senior) Function Quality Engineering / Digital Assurance Experience 8–12 years overall, with 3+ years applying AI/ML or LLMs to engineering workflows Location Offshore ROLE OVERVIEW We are looking for a Senior AI Engineer to join an active, large-scale test automation program and raise its ceiling with AI. You will work alongside automation engineers, SDETs and client QA stakeholders to introduce LLM- and agent-based capabilities into the way tests are designed, generated, maintained and triaged — and, equally, to build the new automation frameworks that make those capabilities usable at scale. This is a hands-on engineering role, not an advisory one. You will ship working tooling into live delivery, prove its value with measurable outcomes, and bring the wider automation team along with you. KEY RESPONSIBILITIES Agentic & LLM-based test generation. Design and build LLM-powered capabilities that generate test cases, test scripts and test data from requirements, user stories, API contracts, designs and existing application behaviour. Framework development. Architect and implement new automation frameworks from the ground up — reusable, framework-agnostic layers for web, API, mobile and data pipelines — with AI capabilities designed in rather than bolted on. Autonomous agents. Build agentic workflows that explore applications, propose coverage, self-heal broken locators and assertions, and keep suites current as the product changes. Integration. Integrate AI tooling into existing suites (Selenium, Playwright, Cypress, Appium, REST Assured, Karate) and CI/CD pipelines so that generation, execution and maintenance run as part of normal delivery. Analytics & triage. Apply ML and LLM techniques to failure triage, flaky-test detection, duplicate-defect clustering and risk-based test selection, reducing manual analysis effort per cycle. Quality of AI output. Define prompts, grounding strategies, retrieval patterns and evaluation harnesses so AI-generated test assets are accurate, deterministic enough to trust, and measurably better than the baseline. Engineering rigour. Deploy and operate models and AI services responsibly — versioning, cost control, observability, data handling and client security and compliance requirements. Enablement. Mentor automation engineers and SDETs on AI-assisted practices, run working sessions and demos, and contribute reusable accelerators and documentation back to the practice. Stakeholder engagement. Work directly with client QA leads, product owners and architects to shape the AI roadmap for the program and report progress against agreed metrics. REQUIRED SKILLS & EXPERIENCE 8–12 years in software engineering, test automation or AI/ML engineering, with at least 3 years building AI/LLM-enabled solutions in production or live delivery. Strong programming ability in Python and/or Java or TypeScript, with clean, tested, reviewable code as a habit. Demonstrable experience with LLM application development: prompt engineering, function/tool calling, RAG, vector stores, embeddings, and at least one agent framework (LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, MCP-based agents or equivalent). Proven track record of designing and building automation frameworks from scratch — architecture, abstraction layers, reporting, test data management, parallel execution. Hands-on depth in at least two of: Playwright, Selenium, Cypress, Appium, API automation, performance or data-quality automation. Solid CI/CD and DevOps practice: Git, Jenkins or GitHub Actions or Azure DevOps, Docker, artifact and environment management. Experience evaluating AI output quality — building eval sets, scoring, regression-testing prompts and models rather than relying on impressions. Ability to work inside an existing program: read someone else's framework, respect delivery timelines, and introduce change incrementally without destabilising live suites. PREFER