SDET L3

Responsibilities: Framework Architecture: Design and build scalable, custom Python-based automation frameworks from scratch to handle end-to-end voice assistant workflows.AI/ML Validation Strategy: Establish methodologies for testing AI/LLM behaviours, including evaluating Word Error Rate (WER), semantic accuracy, hallucinations, and multi-turn conversation context retention.Performance and Scale: Lead the design of infrastructure to simulate thousands of concurrent voice sessions to test system latency, audio degradation, and infrastructure bottlenecks.Tooling and Innovation: Create internal tools or mocks to simulate microphone inputs, network jitter, and telephony interfaces (e. g., VoIP/SIP/WebRTC). Requirements: Experience: 6+ years of experience in software test architecture, development, or automation leadership.Expert Python: Expert-level Python skills with deep knowledge of concurrency, async programming (asyncio), and framework design.Voice/Telecom Domain: Deep understanding of audio streaming protocols, codecs, and WebSockets/gRPC. .