Senior Machine Learning Engineer - Voice Experience

About the role

We are looking for a Senior Machine Learning Engineer, Voice Experience to help build the next generation of AI-powered voice systems for the contact center. In this role, you will work at the intersection of speech, language, and real-time production systems, improving how AI listens, understands, reasons, empathizes, and responds in live customer conversations.

You will develop and improve machine learning systems that power voice experiences end to end, including automatic speech recognition, turn detection, downstream language understanding, retrieval-augmented and agentic workflows, quality measurement, text to speech, and production optimization. You will partner closely with applied researchers, product managers, designers, forward deployed engineers, and platform engineers to ensure model and system improvements translate into measurable customer and business impact.

This role is ideal for someone who is excited by both model quality and production reality: designing rigorous evaluation frameworks, analyzing failure modes, improving latency and robustness, and shipping systems that perform reliably at scale in real-time voice environments.

Responsibilities

• Design, train, evaluate, and deploy machine learning systems that power real-time voice experiences, including ASR, speech understanding, turn detection, text to speech, speech to speech, classification, entity extraction, summarization, and structured insight generation.
• Improve the quality of voice AI systems through error analysis, data curation, metric design, benchmarking, and iterative model improvement, with a strong focus on real-world performance.
• Build evaluation frameworks for complex voice and agentic systems, measuring metrics such as accuracy, robustness, latency, faithfulness, naturalness, professionalism, task completion, and cost.
• Diagnose and mitigate failure modes across the voice stack, including transcription errors, hallucinations, retrieval failures, tool misuse, prompt brittleness, context drift, and multi-step reasoning breakdowns.
• Design and optimize low-latency ML workflows for live conversations, balancing model quality with system responsiveness, scalability, and reliability.
• Partner with platform and backend engineers to productionize real-time inference, streaming pipelines, quality monitoring, and continuous model iteration.
• Collaborate cross-functionally with product, design, frontend, and backend teams to integrate voice intelligence seamlessly into Cresta's platform.
• Establish best practices for offline evaluation, online experiment design, and monitoring of voice ML systems.