Edge ML Engineer: Port Models to Non-NVIDIA & ARM

Deepgram; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

Deepgram is seeking an Applied ML Engineer on the Partner Platform Engineering team to port speech models to edge and non-NVIDIA hardware, ensuring they run within target kernels and runtimes with minimal changes. This is an applied ML role focused on edge deployment, not a research or cloud-serving position.

You will own the deployment path, collaborate with Embedded AI Engineers, and drive measurable results on real devices while shaping how Deepgram ports models across platforms, including

Qualifications

• Hands-on experience deploying ML models to edge or non-NVIDIA hardware in production.
• Strong Python and PyTorch with production-grade engineering habits.
• Experience with model conversion toolchains and edge runtimes.

Responsibilities

• Port Deepgram speech models to non-NVIDIA and edge platforms with minimal modification.
• Own serving-side model decisions for edge targets: quantization, precision, and graph rewrites.
• Validate ports on real hardware with accuracy, latency, throughput, and memory benchmarks.
• Build the deployment path for edge targets: packaging, conversion pipelines, versioning.
• Collaborate with Embedded AI Engineers to integrate custom kernels.
• Partner with platform and silicon vendors on runtimes and toolchains.
• Feed edge constraints back to Research and Impeller for easier porting in future models.
• As the team grows, take on adjacent production concerns at the edge: deployment automation, security, observability.

Skills

Python

PyTorch

Edge deployment

Model porting

Automation

Tools

ONNX Runtime

TFLite

OpenVINO

ExecuTorch

Qualcomm AI Engine

NPU SDK

Job description

Deepgram is seeking an Applied ML Engineer on the Partner Platform Engineering team to port speech models to edge and non-NVIDIA hardware, ensuring they run within target kernels and runtimes with minimal changes. This is an applied ML role focused on edge deployment, not a research or cloud-serving position.

You will own the deployment path, collaborate with Embedded AI Engineers, and drive measurable results on real devices while shaping how Deepgram ports models across platforms, including