Senior Software Engineer - Model Evaluation & AI Systems

Build and scale evaluation and quality-assurance systems that validate speech-to-text, text-to-speech, and LLM/RAG/agent/multimodal models before they ship. Define evaluation methodology, pass/fail gates, and monitoring; design automated pipelines for batch and streaming (e.g., WER and hallucination detection); and integrate quality checks into CI/CD. Partner with Research, model training, inference, and product teams to deliver trusted signals that protect customer experience.