Staff Platform Engineer, Voice AI
$220,000–$280,000 year
On-site · San Francisco, California, United States
Job Summary
Staff Platform Engineer to own the architecture for Together AI's real-time voice platform. Define technical direction for WebSocket and HTTP streaming APIs powering STT/TTS at scale, establish reliability for production voice agents, and lead autoscaling for latency-sensitive workloads across tens of thousands of GPUs. Design the voice API surface, build an observability platform, and manage a multi-provider abstraction layer across model partners. Collaborate with ML serving, drive developer experience and API ergonomics, and architect for future voice products. Requires 8+ years in real-time distributed systems, expert TS/Python, Kubernetes, and domain experience with audio protocols; roles based in San Francisco, USA; compensation $220k–$280k plus equity and benefits.
Required Qualifications
- 8+ years of experience building large-scale real-time distributed systems
- Expert-level TypeScript and Python, with strong proficiency in systems-level thinking; Rust experience is a meaningful advantage
- Senior distributed systems judgment — load balancing, autoscaling, rate limiting, and traffic shaping for latency-sensitive workloads
- Deep Kubernetes expertise — custom autoscalers, resource management, and health checking for stateful, streaming services
- Experience with audio and media protocols (WebRTC, g711, PCM encoding)
- Familiarity with ML model serving infrastructure and how inference engines work
- Bachelor's or Master's in Computer Science, Computer Engineering, or related field — or equivalent depth demonstrated through work
- Strong technical leadership — you set direction, influence across teams, and improve systems/teams
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.