Lead Engineer - AI Agent Voice Experience
$205k - $270k • Remote • United States (Remote)
Posted 1mo ago
Job Location
United States (Remote)
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
We are seeking a Lead Engineer, AI Agent Voice Experience to develop the next generation of AI-powered voice systems for contact centers. This role involves working at the intersection of speech, language, and real-time production systems to enhance how AI listens, understands, reasons, empathizes, and responds in live customer conversations. You will be responsible for developing and improving end-to-end machine learning systems for voice experiences, including automatic speech recognition, turn detection, agentic workflows, voice evaluation, text-to-speech, speech-to-speech models, and production optimization. Collaboration with researchers, product managers, designers, and engineers will be key to translating model improvements into measurable business impact. This position is ideal for individuals passionate about both model quality and production realities, focusing on rigorous evaluation, failure analysis, latency and robustness improvements, and shipping reliable, scalable real-time voice systems.
Responsibilities
- Design, train, evaluate, and deploy ML systems for real-time voice experiences, including speech-to-text, turn detection, text-to-speech, speech-to-speech, reasoning, and structured insight generation.
- Enhance voice AI system quality through error analysis, data curation, metric design, benchmarking, and iterative model improvement, prioritizing real-world performance.
- Build evaluation frameworks for complex voice and agentic systems, measuring metrics like accuracy, robustness, latency, faithfulness, naturalness, professionalism, task completion, and cost.
- Diagnose and mitigate failure modes across the voice stack, such as transcription errors, hallucinations, tool misuse, prompt brittleness, context drift, and multi-step reasoning breakdowns.
- Design, implement, and optimize low-latency ML systems to improve caller experience, including backchanneling, speaker focus, emotion interpretation, and empathetic responses.
- Partner with platform and backend engineers for 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 into Cresta's platform.
- Mentor engineers, contribute to technical strategy, and help shape the roadmap for Cresta’s voice AI systems.
Requirements
- Bachelor's degree in Computer Science, Mathematics, Machine Learning, AI, or a related field; Master's or Ph.D. preferred.
- 5+ years of experience building, evaluating, and deploying ML systems in production.
- Demonstrated experience leading fast-moving, highly technical teams with strong communication skills.
- Distinctive technical vision for the future of voice AI.
- Strong background in speech recognition, speech processing, NLP, generative AI, or voice AI.
- Deep experience with model evaluation, benchmarking, error analysis, and quality improvement for production ML systems.
- Solid understanding of transformer-based models, embeddings, retrieval systems, and large-scale training or inference workflows.
- Experience designing and deploying real-time ML systems with strong requirements for latency, scalability, and reliability.
- Experience building data pipelines and tooling for experimentation, measurement, and large-scale quality analysis.
- Ability to work across research and engineering boundaries to translate ideas into production-grade systems.