10 days ago
San Jose, CA, USASenior
Base Salary
$180k - $450k/yr
Responsibilities
- Provision and scale the speech inference stack in a repeatable, auditable, and reliable manner.
- Harden deployment pipelines for secure, ultra-low-latency production speech services.
- Evolve infrastructure for streaming pipelines, session management, fault tolerance, and speech-to-speech models.
- Collaborate with speech ML researchers to identify latency bottlenecks and implement infrastructure improvements.
- Oversee system health and incident response while defining SLOs for real-time speech workloads.
- Manage capacity planning, cost efficiency, and the hardware lifecycle for the global speech inference fleet.
- Build internal tooling and platform abstractions that improve developer experience for speech infrastructure teams.
Requirements
- 5+ years of infrastructure, systems, or platform engineering experience, including at least 2 years in real-time or low-latency environments.
- Experience deploying and managing large-scale inference frameworks or streaming infrastructure.
- Advanced proficiency in at least one systems-level or infrastructure-focused programming language.
- Deep understanding of networking fundamentals for real-time audio and low-latency inference, such as WebRTC or gRPC.
- Experience with container orchestration, job scheduling, and multi-tenant resource management.
- Technical ownership of production systems requiring high reliability and strict latency constraints.
- Strong debugging and observability capabilities across the infrastructure stack.
- Bonus: expertise in Kubernetes, including GPU-aware orchestration and latency-sensitive workloads.
- Bonus: proficiency with Pulumi or comparable Infrastructure as Code frameworks.
- Bonus: advanced Rust or Go experience for systems tooling and performance-critical services.
- Bonus: familiarity with ASR, TTS, end-to-end speech-to-speech architectures, and streaming technologies such as Kafka, WebSockets, or custom audio protocols.
Benefits
- Full-time position with a US base salary range of $180,000-$450,000 annually.
- Additional compensation components and benefits may be included depending on the specific role.
- The posting does not specify a work arrangement or other practical logistics.
Tech Stack
Categories
