Senior Automation Tester in Python (for Gen AI powered applications)

EPAM is a global leader in AI transformation engineering and integrated consulting, serving Forbes Global 2000 companies and ambitious startups. With over thirty years of expertise in custom software, product and platform engineering, EPAM empowers its clients to become AI-Native enterprises, driving measurable value from innovation and digital investments.

• 5+ years of hands-on QA/test automation experience
• Expertise in building and maintaining automated test suites from scratch using Playwright, Selenium, Cypress, and pytest
• Skills in API and backend test automation, including REST APIs, microservices, and serverless architectures with Postman/Newman and pytest + requests
• Proficiency in Python as the primary automation language, with ability to write harnesses, fixtures, and utilities independently
• Knowledge of CI/CD test integration, embedding automated tests into pipelines such as Jenkins and GitHub Actions with quality gates
• Background in testing AI/GenAI applications, validating non-deterministic AI/LLM outputs for accuracy, RAG relevance, hallucination, and prompt regression
• Familiarity with AI/ML model testing, including accuracy, bias, and performance validation using RAGAS, LLM-as-judge, and golden datasets
• English proficiency at B2 level or higher

Nice to have:

• Background in pharmaceutical / life sciences domain, with GxP awareness and IQ/OQ/PQ qualification
• Experience with Jira/Xray, TestRail, or Zephyr test management
• Skills in performance/load testing using JMeter and Locust
• Understanding of security testing basics such as OWASP
• Familiarity with AWS services including Lambda, API Gateway, S3, and CloudWatch

• Build automated test frameworks from scratch for AI-powered clinical applications using Playwright, Selenium, and pytest
• Design and execute test strategies for non-deterministic AI/GenAI outputs, including accuracy, RAG relevance, hallucination checks, and prompt regression
• Integrate automated tests into CI/CD pipelines with quality gates such as block-on-failure and coverage thresholds
• Execute GxP-compliant IQ/OQ/PQ scripts and generate qualification evidence packages
• Manage AI-specific test data, including edge cases, adversarial inputs, and golden datasets
• Monitor model drift, regression, and performance degradation over time
• Produce test strategy documents, test plans, and compliance-ready test evidence
• Collaborate with Data Scientists and Backend Developers to define testable acceptance criteria for AI features