Applied ML Engineer, Edge Devices at Deepgram

Confirmed open

Deepgram seeks a US-remote ML engineer to adapt speech models for edge hardware, benchmark them on devices and automate model conversion and deployment.

Deepgram

Location: Remote
Advertised region: USA - Remote / United States
Employment: FullTime
Work arrangement: remote
Technologies: Python, PyTorch

Create a free application profile — Keep your skills and projects in a reusable profile. Private by default; you choose when to share. Apply for this job directly with the employer.

Role overview

This role ports Deepgram models to edge and non-NVIDIA hardware, with accuracy, latency and memory measured on physical devices. The posting lists remote work in the United States.

Responsibilities

Apply quantization, graph changes and operator replacements to fit models to device constraints; benchmark each port on real hardware.
Create repeatable packaging, conversion and delivery pipelines and work with embedded engineers and platform vendors on runtimes and kernels.

Qualifications

Production experience deploying ML to edge or non-NVIDIA devices is required, as are quantization knowledge, a vendor runtime or ONNX Runtime, TFLite or ExecuTorch, and strong Python and PyTorch.
Experience with speech or audio models, low-level kernels, model security or multiple accelerator families is helpful.

Technology in this role

Python: Production experience deploying ML to edge or non-NVIDIA devices is required, as are quantization knowledge, a vendor runtime or ONNX Runtime, TFLite or ExecuTorch, and strong Python and PyTorch.

How to apply

Review the original posting and apply through the employer’s careers page.

View source and apply Apply directly

Source checked: 2026-10-22

Browse job categories

Python AI and machine learning engineer jobs in Vietnam