Staff ML Engineer: Real-Time Voice Inference Lead

Togetherai; San Francisco (CA); On-site; USD 220,000 - 280,000; Full time

Benefits offered by this job

Competitive compensation

Startup equity

Health insurance

Other competitive benefits

Job summary

Togetherai is looking for a Staff ML Engineer based in San Francisco, California to optimize their voice AI platform. In this role, you will influence the model serving layer for voice workloads while working with advanced inference engines.

The ideal candidate should have over 8 years of experience in ML engineering, particularly focused on model serving, with proven expertise in Python and GPU optimization.

Qualifications

• 8+ years of ML engineering experience, with a focus on model serving.
• Proficiency in LLM serving engines and GPU optimization.
• Experience with architectural decisions that influenced platform evolution.

Responsibilities

• Drive technical strategy for optimizing voice model serving.
• Lead productionization of voice models at scale.
• Build a rigorous model evaluation framework.

Skills

ML engineering experience

Model serving expertise

Python proficiency

GPU optimization

System design judgment

Technical leadership

Speech and audio ML knowledge

Education

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

Tools

PyTorch

TensorRT-LLM

CUDA

Job description

Togetherai is looking for a Staff ML Engineer based in San Francisco, California to optimize their voice AI platform. In this role, you will influence the model serving layer for voice workloads while working with advanced inference engines.

The ideal candidate should have over 8 years of experience in ML engineering, particularly focused on model serving, with proven expertise in Python and GPU optimization.