AI Test Automation Engineer Intern

AI Prof; Hyderabad; On-site; INR 279,000 - 335,000; Full time

Benefits offered by this job

Stipend ₹25k-₹30k/month

Internship to full-time hire

Hands-on AI evaluation experience

CI/CD & Observability exposure

Mentorship and growth opportunities

Job summary

AI.Prof is seeking an AI Test Automation Engineer Intern to design and build automated testing for modern AI-powered applications. You will work across UI automation, APIs, and backend systems, including LLMs and Voice AI, to evaluate non-deterministic AI behavior and ensure production readiness.

You will develop reusable test frameworks, integrate AI tooling, and help improve test coverage and reliability across real-time and distributed systems.

Qualifications

• Final year student with no backlogs and CGPA above 7.5 or equivalent.
• Portfolio of automation/testing projects recommended.

Responsibilities

• Design and build automated testing for UI, APIs, and backend systems.
• Create evaluation frameworks for AI outputs including LLMs and non-deterministic behavior.
• Automate web and mobile testing using Playwright, Cypress, Selenium, Appium, or equivalents.
• Validate REST APIs, services, databases, and data flows.
• Build AI evaluation pipelines and synthetic test data for production readiness.
• Identify flaky tests, performance bottlenecks, and root causes.

Skills

Test automation frameworks

APIs & backend testing

AI testing fundamentals

Automation framework design

Modern AI tooling

Education

Final year student CGPA > 7.5

Tools

Playwright

Cypress

Selenium

Appium

PyTest

Jest

Job description

Our Quality Engineering team builds the testing and evaluation systems that ensure our AI-powered products are reliable, scalable, and production-ready. We test across AI workflows, web and mobile applications, APIs, real-time systems, and distributed services.We don't treat testing as a final checkpoint. We build automated quality infrastructure that continuously identifies functional defects, AI failures, performance regressions, reliability issues, and poor user experiences before they reach production.

About the Role

As an AI Test Automation Engineer Intern, you will design and build automated testing and evaluation systems for modern AI-powered applications. You will work across UI automation, APIs, backend systems, LLMs, Voice AI, real-time workflows, and distributed services.You will go beyond traditional QA by building systems that can evaluate non-deterministic AI behavior, detect regressions, measure quality, and continuously validate production readiness using modern AI testing tools, evaluation frameworks, synthetic data, and AI-assisted development workflows.

What You'll Do

• Build Automated Test Infrastructure: Design and maintain scalable automated test suites covering functional, regression, integration, and end-to-end workflows.
• Test AI Systems: Create evaluation frameworks for LLM and AI outputs, measuring correctness, relevance, consistency, safety, latency, and failure behavior.
• Automate Web & Mobile Testing: Build reliable UI and cross-platform test automation using tools such as Playwright, Cypress, Selenium, Appium, or equivalent frameworks.
• Test APIs & Backend Systems: Validate REST APIs, services, databases, data flows, authentication, integrations, and distributed system behavior.
• Engineer AI Evaluation Pipelines: Build automated test datasets, synthetic test scenarios, evaluation pipelines, and LLM-as-a-judge or rule-based evaluation systems.
• Test Real-Time Systems: Validate streaming, WebSocket, Voice AI, asynchronous workflows, notifications, and failure recovery under real-world conditions.
• Engineer for Reliability: Identify flaky tests, race conditions, edge cases, concurrency issues, performance bottlenecks, and failure modes.
• Leverage Modern AI Tools: Use AI coding agents, test-generation tools, synthetic data generation, automated debugging, log analysis, and AI evaluation frameworks to increase testing velocity and coverage.
• Build Performance & Load Tests: Design tests that evaluate system behavior under increasing traffic, concurrency, latency, and resource constraints.
• Drive Root Cause Analysis: Investigate failures beyond surface-level symptoms and work with engineers to identify and prevent recurring issues.
• Own Quality End to End: Define quality requirements, automate validation, monitor production behavior, and continuously improve test coverage and reliability.

What We're Looking For

Technical

• Test Automation: Hands-on experience with Playwright, Cypress, Selenium, Appium, PyTest, Jest, or equivalent testing frameworks.
• Software Engineering: Strong understanding of Git, debugging, version control, APIs, databases, data structures, and clean code practices.
• API & Backend Testing: Understanding of REST APIs, HTTP, authentication, JSON, database validation, and distributed application behavior.
• AI Testing Fundamentals: Understanding of LLMs, prompting, structured outputs, embeddings, hallucinations, non-deterministic behavior, and AI evaluation challenges.
• Automation Engineering: Ability to design reusable test frameworks rather than writing isolated scripts.
• Modern AI Tooling: Experience using AI coding assistants, automated test-generation tools, or AI evaluation frameworks to improve engineering productivity.

Good to Have

• LLM Evaluation: Experience with LLM evaluation frameworks, LLM-as-a-judge, benchmark datasets, tracing, or experiment tracking.
• Performance Testing: Experience with k6, Locust, JMeter, or equivalent load-testing tools.
• Real-Time Systems: Exposure to WebSockets, WebRTC, streaming systems, asynchronous processing, or Voice AI.
• Mobile Automation: Experience with Appium, Android/iOS testing, or Flutter testing.
• CI/CD: Experience integrating automated tests into GitHub Actions, GitLab CI, Jenkins, or similar pipelines.
• Observability: Familiarity with logs, metrics, traces, monitoring, and tools such as Grafana, Prometheus, or OpenTelemetry.
• Cloud & Containers: Exposure to Docker, Kubernetes, AWS, Azure, GCP, or cloud-based testing environments.

Mindset

• Extreme Attention to Detail: Identify subtle failures, edge cases, inconsistencies, and regressions others may overlook.
• Engineering Mindset: Treat testing as software engineering not manual verification or checklist execution.
• AI Curiosity: Understand how AI systems fail and continuously explore better ways to evaluate them.
• Extreme Ownership: Own quality gaps from discovery through root cause analysis and prevention.
• Bias to Automation: If a test will be repeated, look for a way to automate it reliably.
• Root Cause Thinking: Don't just report failures. Investigate why they happened and help prevent recurrence.
• Clear Technical Communication: Produce precise, reproducible bug reports and communicate technical findings clearly.
• Resourcefulness: Use modern tools, automation, and AI to maximize test coverage and engineering efficiency.

Qualifications

• Academic Standing: Final year student with no active backlogs and a CGPA above 7.5, recent graduate, or equivalent candidate with strong analytical and technical capability.
• Demonstrated Track Record: Portfolio of meaningful software, automation, testing, or AI projects through GitHub, hackathons, internships, research, or personal projects.
• Hands-On Experience: Experience building an application and testing it through automation, APIs, integration testing, or other engineering quality practices.
• Problem Solving Ability: Strong ability to investigate complex failures, reason systematically, and identify root causes.
• Technical Curiosity: Genuine interest in software quality, AI systems, automation, and understanding how complex systems behave under failure.

Why This Role

Testing AI-driven learning workflows, customized LMS environments, real-time Voice interaction, and student-facing applications is a high-impact engineering role. You won't be running repetitive manual checklists you will build an automated quality framework that protects what thousands of students experience on our customized platform every day.

What You'll Get

• High-Impact Stipend: ₹25,000 - ₹30,000 / month based on technical capability, execution, and demonstrated impact.
• FastTrack Career Growth: Top performers convert to a full-time role with a package of ₹6-10 LPA, based on impact and ownership shown during the internship.
• Real Engineering Ownership: Build testing infrastructure that protects production systems rather than executing predefined QA checklists.
• AI Evaluation Expertise: Gain hands‑on experience evaluating LLMs, AI agents, Voice AI, and other non-deterministic systems.
• Modern Automation Stack: Work with contemporary testing, observability, CI/CD, performance, and AI development tools.
• End-to-End Exposure: Work across frontend, backend, APIs, AI systems, databases, infrastructure, and production workflows.

Our Culture

This is not an ordinary QA internship. We are building the quality and reliability foundation for AI powered products, where testing requires engineering depth, analytical thinking, speed, and relentless attention to detail.From day one, you are expected to think beyond finding bugs. Understand how systems fail, build mechanisms to detect those failures automatically, and help engineer them out of the system permanently.

Our Non‑Negotiables

• Uncompromising Honesty: Report failures clearly, even when they expose gaps in your own work or the team's assumptions.
• Hard Work & Humility: High execution capacity with the humility to learn, accept feedback, and improve.
• Relentless Excellence: Quality is the baseline. Continuously raise coverage, reliability, and testing depth.
• Extreme Ownership: Own quality outcomes end to end. There is no "someone else will catch it."
• Bias to Automation: Eliminate repetitive manual work through reliable, maintainable automation.
• Root Cause Thinking: Do not stop at identifying a failure. Understand why it happened and prevent it from recurring.
• AI Native Resourcefulness: Leverage modern AI tools, evaluation frameworks, and automation technologies to dramatically improve testing velocity and coverage.
• Engineering Discipline: Tests must be deterministic where possible, maintainable, observable, and trusted by the engineering team.
• Solve Aggressively, Ask Fearlessly: Investigate difficult failures independently while raising blockers and asking precise questions early.
• Disagree Openly, Commit Fully: Challenge quality strategies and technical assumptions with evidence, debate rigorously, and fully commit once a direction is selected.

Note :

Equal Opportunity Employer: AI.Prof is proud to be an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees regardless of race, color, religion, sex, sexual orientation, gender identity, national origin, veteran, or disability status.