Audio Inference Engineer, Model Efficiency
Core
Build reliable machine learning systems and optimize audio inference serving efficiency using innovative techniques.
Role type
Senior IC machine-learning engineer (audio inference efficiency)
Builds
Real-time and streaming audio inference systems
Domain
AI / Audio Processing / Distributed Systems
Deliverable
production ML models
Required skills
C++, Python, deep learning models for audio/speech, high-performance inference system development, system bottleneck identification, creative solution design for audio processing
Preferred skills
GPU programming, low-level system optimization, model parallelization over multiple GPUs, duplex real-time streaming architectures, machine learning framework internals (PyTorch, TensorFlow), inference frameworks (vLLM, SGLang, Tensort-LLM), sequence modeling (transformers for audio/speech), end-to-end audio pipeline optimization
Technologies
C++, Python, PyTorch, TensorFlow, vLLM, SGLang, Tensort-LLM
Responsibilities
Advance core audio model serving metrics (latency, throughput, quality), dive deep into systems to identify bottlenecks, deliver creative solutions for audio processing and streaming workloads, collaborate with training and serving infrastructure teams for seamless integration
Seniority
Senior, hands-on IC