Senior ML Engineer, Voice AI — Real-Time Inference Lead

Together AI; San Francisco (CA); Sur place; USD 200 000 - 260 000; Plein temps

Avantages offerts par ce poste

Competitive salary

Startup equity

Health insurance

Other competitive benefits

Résumé du poste

An AI infrastructure company is looking for a Senior ML Engineer to optimize performance for voice models such as speech-to-text and text-to-speech. You will work on productionizing models on advanced serving engines, focusing on GPU utilization and inference optimization. With over 5 years of experience required, this role offers competitive compensation in San Francisco, California, and invites you to be part of a visionary team shaping the future of voice applications.

Qualifications

• 5+ years of experience in ML engineering, focusing on model serving and inference optimization.
• Hands-on experience with LLM serving engines and optimization.
• Strong proficiency in Python and PyTorch; experience with GPU profiling.

Responsabilités

• Optimize inference performance for voice models including STT and TTS.
• Productionize voice models on serverless and dedicated endpoints.
• Build and maintain a voice model evaluation framework.

Connaissances

ML engineering

Model serving

Inference optimization

Python

PyTorch

CUDA

Formation

Bachelor's or Master's degree in Computer Science or related field

Outils

TensorRT‑LLM

vLLM

SGLang

Description du poste

An AI infrastructure company is looking for a Senior ML Engineer to optimize performance for voice models such as speech-to-text and text-to-speech. You will work on productionizing models on advanced serving engines, focusing on GPU utilization and inference optimization. With over 5 years of experience required, this role offers competitive compensation in San Francisco, California, and invites you to be part of a visionary team shaping the future of voice applications.