SDET - III (RAGas Automation Testing)

Zealant Consulting Group; India; In loco; INR 1.200.000 - 1.800.000; Tempo pieno

Descrizione del lavoro

Zealant Consulting Group is seeking a QA/SDET expert in India to design, build, and maintain automation frameworks for AI-powered products. You will test AI features, validate RAG flows, and push for high-quality releases across teams.

The role emphasizes independent work, mentorship of junior engineers, and collaboration with AI researchers to tackle complex testing challenges in AI/ML domains. Prior experience with Playwright/Cypress/Selenium is valuable for success.

Competenze

• 5+ years of overall experience in QA/SDET roles
• Proven experience working with AI tools (e.g., OpenAI, Claude, or similar LLM platforms)
• Strong understanding of testing AI/ML products and their unique challenges
• Hands-on knowledge of RAG pipelines and their testing methodologies
• Proficiency in automation frameworks (Playwright, Cypress, Selenium, or similar)
• Experience with API testing (Postman, REST, GraphQL, gRPC)
• Strong problem-solving skills with the ability to work independently
• Mentorship and leadership skills in guiding peers or junior engineers

Mansioni

• Design, develop, and maintain automation frameworks and test strategies for AI products
• Test and validate AI-powered features (including OpenAI, Claude, and other AI integrations)
• Evaluate and improve RAG (Retrieval-Augmented Generation) flows, ensuring accuracy and performance
• Leverage AI automation tools to optimize test coverage and efficiency
• Collaborate closely with developers, product managers, and AI researchers to ensure high-quality releases
• Own tasks end-to-end, working independently to deliver on commitments
• Mentor and guide junior SDETs, fostering a culture of quality and continuous learning

Conoscenze

QA/SDET experience

AI tools

AI/ML testing

RAG testing

Automation frameworks

API testing

Problem-solving

Mentorship

Strumenti

Playwright

Cypress

Selenium

Postman

REST

GraphQL

gRPC

Descrizione del lavoro

• 5+ years of overall experience in QA/SDET roles
• Proven experience working with AI tools (e.g., OpenAI, Claude, or similar LLM platforms)
• Strong understanding of testing AI/ML products and their unique challenges
• Hands-on knowledge of RAG pipelines and their testing methodologies
• Proficiency in automation frameworks (e.g., Playwright, Cypress, Selenium, or similar)
• Experience with API testing (Postman, REST, GraphQL, gRPC)
• Strong problem-solving skills with the ability to work independently
• Mentorship and leadership skills in guiding peers or junior engineers
  

Requirements

• 5+ years of overall experience in QA/SDET roles
• Proven experience working with AI tools (e.g., OpenAI, Claude, or similar LLM platforms)
• Strong understanding of testing AI/ML products and their unique challenges
• Hands-on knowledge of RAG pipelines and their testing methodologies
• Proficiency in automation frameworks (e.g., Playwright, Cypress, Selenium, or similar)
• Experience with API testing (Postman, REST, GraphQL, gRPC)
• Strong problem-solving skills with the ability to work independently
• Mentorship and leadership skills in guiding peers or junior engineers
  

Responsibilities

• Design, develop, and maintain automation frameworks and test strategies for AI products
• Test and validate AI-powered features (including OpenAI, Claude, and other AI integrations)
• Evaluate and improve RAG (Retrieval-Augmented Generation) flows, ensuring accuracy and performance
• Leverage AI automation tools to optimize test coverage and efficiency
• Collaborate closely with developers, product managers, and AI researchers to ensure high-quality releases
• Own tasks end-to-end, working independently to deliver on commitments.
• Mentor and guide junior SDETs, fostering a culture of quality and continuous learning
  

Nice to have

• Experience with CI/CD pipelines and cloud platforms (AWS/GCP/Azure)
• Familiarity with MLOps pipelines and monitoring AI systems
• Exposure to performance and scalability testing of AI workloads
  

Skills: llm testing,ragas,ai test engineer,retrieval testing,prompt engineering,rag evaluation,python,javascript