Edge ML Engineer: Port & Optimize Models to Edge Hardware

Devconnectplatform; United States; Remote; USD 155,000 - 245,000; Full time

Job summary

Deepgram is seeking an Applied ML Engineer for edge devices to port and optimize speech models on non-NVIDIA hardware. The role focuses on adapting models to target kernels, runtime constraints, and device limits while preserving accuracy and latency.

The position emphasizes hands-on deployment, automated edge tooling, and collaboration with Embedded AI to ship reliable models to customers from edge devices.

Qualifications

• Hands-on experience deploying ML models to edge or non-NVIDIA hardware in production.

Responsibilities

• Port Deepgram speech models to non-NVIDIA and edge platforms with minimal modification.
• Own serving-side model decisions for edge targets: quantization, precision, op substitutions, graph rewrites.
• Validate port accuracy, latency, throughput, and memory on real hardware across platforms.
• Build and maintain the deployment path for edge targets with versioning and automated delivery.

Skills

Python

PyTorch

Edge deployment

Model porting

Quantization

Latency benchmarking

Tools

ONNX Runtime

TFLite

ExecuTorch

OpenVINO

Job description

Deepgram is seeking an Applied ML Engineer for edge devices to port and optimize speech models on non-NVIDIA hardware. The role focuses on adapting models to target kernels, runtime constraints, and device limits while preserving accuracy and latency.

The position emphasizes hands-on deployment, automated edge tooling, and collaboration with Embedded AI to ship reliable models to customers from edge devices.