Senior ML Engineer, Voice AI Inference

Together Computer Inc; San Francisco (CA); Presencial; USD 200.000 - 260.000; Jornada completa

Descripción de la vacante

Together AI, the AI Native Cloud, is building high-performance inference for voice applications. We are hiring a Senior ML Engineer to own the model serving stack for STT, TTS, and speech-to-speech, optimizing latency and throughput on GPUs.

You will work hands-on with engines like vLLM, SGLang, and TensorRT-LLM, profile GPU usage, and design batching for streaming audio while collaborating with partners to productionize models.

Formación

• 5+ years of ML engineering experience focused on model serving or ML infrastructure.
• Hands-on experience with LLM serving engines (vLLM, SGLang, TensorRT-LLM)
• Strong proficiency in Python and PyTorch; GPU profiling and optimization (CUDA, memory management)
• Track record of shipping ML systems to production with measurable performance improvements.
• Strong product sense for developers building voice apps
• Experience in a small, fast-moving team environment
• Experience with speech and audio ML (ASR, TTS) is a plus but not required

Responsabilidades

• Own the model serving stack powering the voice platform (STT, TTS, speech-to-speech).
• Productionize voice models with batching, streaming inference, and memory management for audio workloads.
• Build and maintain voice model evaluation frameworks (WER, latency, naturalness).
• Enable new model architectures in the serving stack as the field evolves.
• Collaborate with model partners to integrate external models on Together's infra.
• Profile and debug the full inference stack from GPU kernels to framework bottlenecks.
• Work with platform engineering to meet latency and reliability targets for real-time APIs.
• Contribute to fine-tuning capabilities for customers creating differentiated voice experiences.
• Lay groundwork for multiple new products.

Conocimientos

Model serving

Inference optimization

Python

PyTorch

GPU profiling

Production ML systems

Product sense

Team collaboration

Educación

Bachelor's or Master's in CS/EE or related field

Herramientas

vLLM

SGLang

TensorRT-LLM

Descripción del empleo

Together AI, the AI Native Cloud, is building high-performance inference for voice applications. We are hiring a Senior ML Engineer to own the model serving stack for STT, TTS, and speech-to-speech, optimizing latency and throughput on GPUs.

You will work hands-on with engines like vLLM, SGLang, and TensorRT-LLM, profile GPU usage, and design batching for streaming audio while collaborating with partners to productionize models.