[ engineering ]
Software Engineer - Voice Ai (inference Runtime)
Baseten- Location
- Remote
- Work mode
- Remote
- Type
- full time
- Listed
Applications go directly to Baseten. Ramai takes no fee for placement and no money for ranking.
[ About this role ]
Software Engineer - Voice AI (inference Runtime) at Baseten. This role focuses on building and owning Baseten's in-house inference stack for Voice AI models. Responsibilities include developing a model serving stack for open-source voice models, optimizing latency and throughput, and building real-time infrastructure for multi-model voice agents.
Skills and focus areas
- voice ai
- inference
- model serving
- latency optimization
- throughput optimization
- gpu efficiency
- runtime tuning
- server-level optimizations
- real-time infrastructure
- streaming i/o
- distributed systems
Summary written by Ramai from the original posting. Full details and requirements are on Baseten’s careers page.
[ More at Baseten ]
See all 104 open roles at Baseten →[ Similar roles at other startups ]
Browse all open engineering roles →[ Not quite right? ]
Tell the assistant what you’re after — stage, location, stack, visa sponsorship — and it searches every open role for you. A few questions are free, no account needed.