Speechify aims to solve the problem of reading being a barrier to learning by providing text-to-speech products that allow users to consume information through audio. The company is looking for someone to deploy and operate the core ML inference workloads for their AI Voices serving pipeline, improving performance, latency, throughput, and efficiency of deployed models.
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 such as Code, Docker, and containerized deployments.
- Experience deploying high-availability applications on Kubernetes.
- Experience deploying ML models to production
Responsibilities
- Work alongside machine learning researchers, engineers, and product managers to bring our AI Voices to their customers for a diverse range of use cases
- Deploy and operate the core ML inference workloads for our AI Voices serving pipeline
- Introduce new techniques, tools, and architecture that improve the performance, latency, throughput, and efficiency of our deployed models
- Build tools to give us visibility into our bottlenecks and sources of instability and then design and implement solutions to address the highest priority issues
Other
- Think strategically
- Enjoys fast-paced environments
- Passionate about making product decisions
- Experience building great user experiences that delight users
- Work ethic, solid communication skills, and obsession with winning are paramount.
