SDET

Job Title: SDET – Python + AI / Test Automation (Agent-Based Testing)
Location: Remote

Need only H1B consultants

Role Overview
We are seeking a highly skilled Software Development Engineer in Test (SDET) with strong expertise in Python-based automation and AI-driven testing. The role focuses on designing and building intelligent test agents, validating LLM-powered and agentic systems, and enabling scalable, automation-first quality engineering practices.
The ideal candidate will have hands-on experience in test automation frameworks, API testing, and AI/LLM validation techniques, with the ability to work in fast-paced Agile environments.

Key Responsibilities
•    Design and develop scalable automation frameworks using Python (Pytest / Playwright / Requests / Async frameworks) 
•    Build and implement AI-powered test agents for autonomous test execution, validation, and monitoring 
•    Validate LLM-based applications using techniques like: 
•    Semantic similarity validation 
•    Response relevance & grounding checks 
•    Hallucination and robustness detection 
•    Implement prompt-based testing strategies and adversarial test scenarios for AI systems 
•    Develop API, UI, and event-driven test automation for microservices architectures 
•    Integrate automation suites into CI/CD pipelines (GitHub Actions / Jenkins / Azure DevOps) 
•    Design test data strategies for AI and non-AI systems, including synthetic data generation 
•    Work closely with product, engineering, and AI teams to define test strategies and quality gates 
•    Build observability-driven validation using logs, metrics, and traces (DataDog or similar) 
•    Ensure high test reliability, low flakiness, and optimized execution in distributed environments 
Required Skills & Experience
Core Engineering
•    7- 10 years of experience in test automation / SDET role 
•    Strong programming skills in Python 
•    Expertise in: 
•    Pytest framework /Playwright (Python) / Selenium (Python) 
•    API testing using Requests / HTTP clients 
•    Experience with test framework design (POM, modular, reusable architecture) 
AI / Automation (Must-Have)
•    Hands-on experience with LLM validation techniques (e.g., semantic scoring, prompt validation) 
•    Experience using tools like DeepEval / LangChain / OpenAI / Azure OpenAI 
•    Understanding of: 
•    Agentic workflows / AI agents 
•    Prompt engineering & evaluation strategies 
•    Experience testing chatbots / generative AI applications / conversational systems 
•    Knowledge of test agent orchestration frameworks 
Automation & DevOps
•    CI/CD integration (GitHub Actions, Jenkins, Azure DevOps) 
•    Experience with Docker / containerized test execution 
•    Familiarity with cloud platforms (AWS / Azure) 
API & System Testing
•    Strong experience in REST API, microservices, and event-driven systems (Kafka / queues) 
•    Experience in contract testing and integration testing 
Nice to Have
•    Experience testing chatbots and Agentic AI .
•    Experience with Model Context Protocol (MCP) or AI governance frameworks 
•    Exposure to performance testing for AI systems 
•    Experience in regulated domains (Healthcare / Life Sciences )