Senior System Software Engineer, Speech AI
Core
Senior System Software Engineer building and optimizing GPU-accelerated speech AI systems (ASR, TTS, ALM, S2S) for enterprise and developer customers.
Role type
Senior System Software Engineer (Speech AI)
Builds
GPU-accelerated speech AI systems, client SDKs, and low-latency inference pipelines
Domain
Artificial Intelligence, Speech Processing, High-Performance Computing
Deliverable
production ML models
Required skills
C++, Python, CUDA, low-latency audio processing, model integration, API/gRPC/Websockets, debugging, performance optimization
Preferred skills
embedded systems, edge deployment, open-source ML contributions
Technologies
CUDA, C++, Python, gRPC, Websockets, HTTP REST, Flashlight, WFST, CTC
Responsibilities
Implement and optimize ASR, TTS, ALM, and S2S systems in production; develop C++ and Python backend implementations; optimize inference latency and throughput; build client SDKs and CLI tools; provide advanced technical guidance to customers
Seniority
Senior, hands-on IC