Senior System Software Engineer - Dynamo and Triton Inference Server
NVIDIAFull Time
Senior (5 to 8 years)
Candidates should have experience shipping Python-based services and be responsible for the successful operation of critical production services. Experience with public cloud environments, particularly GCP, is required, along with expertise in Infrastructure as Code, Docker, and containerized deployments. Preferred qualifications include experience deploying high-availability applications on Kubernetes and deploying ML models to production.
The Senior Software Engineer will collaborate with machine learning researchers, engineers, and product managers to deliver AI Voices to customers. This role involves deploying and operating core ML inference workloads for the AI Voices serving pipeline, introducing new techniques and architecture to improve performance, latency, throughput, and efficiency, and building tools for visibility into bottlenecks and instability, followed by designing and implementing solutions.
Text-to-speech application for accessibility
Speechify provides a text-to-speech application that helps users access information audibly. It is designed for a diverse audience, including students, professionals, and individuals with learning differences like dyslexia and ADHD. The application works by converting written text into spoken words, allowing users to listen to content through various platforms, including a Google Chrome extension, web app, and mobile apps for iOS and Android. This accessibility feature is particularly beneficial for those who prefer auditory learning or have difficulty reading. Unlike many competitors, Speechify offers a freemium model, where basic features are free, and advanced options are available through a subscription. This approach, along with partnerships with platforms like Medium and the Star Tribune, helps expand its reach to over 20 million users worldwide. The goal of Speechify is to eliminate reading barriers, enabling users to learn and retain information more effectively.