Job Description

Senior Software Development Engineer in Test (SDET 4) - AI & Agentic Platforms

Location: Bengaluru, India (hybrid) | Type: Full-Time | Team: Engineering

Reimagine How The World Communicates with AI

We are building the backbone for the next generation of human communication. Imagine a system that doesn't just transmit voice and video, but understands it in real-time, transcribing, summarizing and retrieving context across millions of concurrent sessions

We are seeking a Senior SDET (Level 4) to spearhead the quality engineering efforts for our next-generation AI and Agentic applications. In this role, you will go beyond traditional automation to build frameworks capable of validating Large Language Models (LLMs), autonomous agents, and complex platform integrations.

Key Responsibilities

AI & Agentic Strategy: Design and implement comprehensive test strategies for AI-driven features, focusing on model accuracy, hallucination detection, and the reliability of agentic workflows.
Framework Development: Build and maintain scalable automation frameworks using tools like Playwright, Selenium, and modern JS-based runners (e.g., Testcafe, Cypress) to support AI platform validation.
Infrastructure & CI/CD: Setup and maintain complex test environments, integrating automated AI evaluations into Jenkins/GitLab CI pipelines.
Advanced Testing: Lead R&D efforts to choose the best tools for performance, API, and scalability testing of AI microservices.
Technical Leadership: Conduct code reviews, establish coding standards, and provide technical guidance to the team on AI testing best practices.
Cross-functional Collaboration: Work closely with Architects, Data Scientists, and Product Managers to define "quality" in the context of non-deterministic AI outputs.

Required Qualifications

Experience: 10–15 years in software automation engineering.
Core Tools: Proven mastery of Playwright and Selenium.
AI Observability & Eval: Experience with LLM evaluation tools (e.g., LangSmith, Ragas, or Arize Phoenix) and model-based testing.
AI/ML Testing: Experience or deep knowledge in testing AI agents, LLM prompting, or data-driven systems.
Programming: High proficiency in Java, Python and JavaScript/TypeScript.
Frameworks: Mastery of PyTest, Jest, or Mocha for building modular, scalable test suites.
Environment Management: 3+ years of experience in test environment setup, maintenance, and CI/CD integration.
Testing Methodologies: Strong background in BDD (Cucumber/Behave), Data-Driven Testing, and Performance/Scalability testing.