ML Engineer II: Audio DL Inference & Deployment

SGS Consulting; Washington (District of Columbia); On-site; USD 120,000 - 180,000; Full time

Job summary

SGS Consulting is seeking an experienced ML Engineer to own end-to-end deep-learning models, from architecture to deployment. You will integrate models into internal workflows via APIs and web UI onboarding, and manage on-call operations for always-on inference.

Expert Python, PyTorch, and ML platform tooling are required, with 2+ years deploying models in production. The role demands advanced degrees in a relevant field and knowledge of audio/signal processing, with strong collaboration across

Qualifications

• Proficiency in Python and PyTorch.
• 2+ years deploying ML models in production.
• Experience operating production services, including on-call, runbooks, and escalation.

Responsibilities

• Own a family of deep-learning models end-to-end: architecture, checkpoints, evaluation pipelines and serving infrastructure.
• Integrate models into internal and cross-functional tools via API and UI onboarding.
• Operate always-on model inference: monitor traffic, tune auto-scaling, redeploy when needed.
• Analyze model evaluations, apply minor fixes and manage version bumps.
• Communicate with model users and tooling owners across domains; serve on-call.

Skills

Python

PyTorch

ML engineering

Audio processing

MOS models

ML platform tooling

Education

Master's or PhD in Electrical Engineering / Audio Engineering / Speech or Signal Processing / Acoustics / Computer Science

Bachelor's degree in CS / EE or related

Tools

Internal ML platform tooling

Job description

SGS Consulting is seeking an experienced ML Engineer to own end-to-end deep-learning models, from architecture to deployment. You will integrate models into internal workflows via APIs and web UI onboarding, and manage on-call operations for always-on inference.

Expert Python, PyTorch, and ML platform tooling are required, with 2+ years deploying models in production. The role demands advanced degrees in a relevant field and knowledge of audio/signal processing, with strong collaboration across