AI Engineer & Researcher, Inference

About the Role

Join our team as an AI Engineer & Researcher focused on Inference to deploy and scale the AI Voices that make reading accessible for millions, directly impacting our core product and user experience.

Responsibilities

• Collaborate with machine learning researchers, engineers, and product managers to integrate AI Voices into customer-facing products.
• Deploy and manage core ML inference workloads for the AI Voices serving pipeline.
• Introduce new techniques, tools, and architectural improvements to enhance the performance, latency, throughput, and efficiency of deployed models.
• Develop tools for identifying bottlenecks and instability, and implement solutions to address high-priority issues.

Requirements

• Experience shipping Python-based services.
• Experience being responsible for the successful operation of a critical production service.
• Experience with public cloud environments (GCP preferred).
• Experience with Infrastructure as Code, Docker, and containerized deployments.

Nice-to-Haves

• Experience deploying high-availability applications on Kubernetes.
• Experience deploying ML models to production.

About the Role Impact

This role offers the opportunity to contribute significantly to a product that changes lives, particularly for users with learning differences, by working at the intersection of artificial intelligence and audio.