Edge AI Engineer: On-Device Models Mastery

Devconnectplatform

United States

Remote

USD 219,000 - 274,000

Full time

11 days ago

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Deepgram seeks an Embedded AI Engineer to optimize and run large speech models on constrained edge hardware. You will write kernels in C/C++/Rust, target non-NVIDIA accelerators, and ensure latency, power, and memory targets are met on embedded platforms.

You will work with edge runtimes and vendor toolchains, collaborating with Applied ML teams to fit models to devices. This is a senior, remote role based in the United States.

Qualifications

  • Proven track record delivering performance-critical code for constrained devices.
  • Experience optimizing models for on-device deployment (quantization, pruning, distillation).
  • Strong understanding of hardware-software interaction in embedded systems.

Responsibilities

  • Write and optimize custom kernels and operators for embedded platforms.
  • Collapse models onto device execution units through quantization and fusion.
  • Integrate with edge runtimes and extend toolchains with custom operators.
  • Develop runtime components for embedded Linux, bare-metal, and RTOS targets.
  • Benchmark latency, power, memory, and accuracy per platform.
  • Collaborate with silicon vendors for SDK integration and tuning.
  • Provide per-platform validation to catch regressions before shipping.

Skills

C/C++ proficiency
Rust
Performance optimization
Embedded systems
Deep learning on edge

Tools

ONNX Runtime
TensorRT
TFLite
ExecuTorch
Vendor NPU toolchains

Job description

Deepgram seeks an Embedded AI Engineer to optimize and run large speech models on constrained edge hardware. You will write kernels in C/C++/Rust, target non-NVIDIA accelerators, and ensure latency, power, and memory targets are met on embedded platforms.

You will work with edge runtimes and vendor toolchains, collaborating with Applied ML teams to fit models to devices. This is a senior, remote role based in the United States.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Embedded AI Engineer — On-Device Models & Edge Optimizations
Embedded AI Engineer — On-Device Models & Edge Optimizations

FDE Times • United States

Remote
USD 150,000 - 230,000
Embedded AI Engineer: On-Device Speech & Edge Inference
Embedded AI Engineer: On-Device Speech & Edge Inference

Deepgram • United States

On-site
USD 140,000 - 190,000
Embedded AI Engineer: On-Device Models & Edge Kernels
Embedded AI Engineer: On-Device Models & Edge Kernels

Deepgram • San Francisco (CA)

On-site
USD 130,000 - 195,000
Edge ML Engineer: Port & Optimize Models to Edge Hardware
Edge ML Engineer: Port & Optimize Models to Edge Hardware

Devconnectplatform • United States

Remote
USD 155,000 - 245,000
On-Device AI Engineer: Edge Model Optimization
On-Device AI Engineer: Edge Model Optimization

Deepgram • United States

Remote
USD 140,000 - 210,000
Edge ML Engineer: Port Models to Non-NVIDIA & Devices
Edge ML Engineer: Port Models to Non-NVIDIA & Devices

Deepgram • San Francisco (CA)

On-site
USD 150,000 - 230,000
Edge ML Engineer - Deploy ML on Non-NVIDIA Platforms
Edge ML Engineer - Deploy ML on Non-NVIDIA Platforms

FDE Times • United States

Remote
USD 140,000 - 210,000
Embedded AI Engineer, On-Device Models
Embedded AI Engineer, On-Device Models

FDE Times • United States

Remote
USD 150,000 - 230,000
Embedded AI Engineer, On-Device Models
Embedded AI Engineer, On-Device Models

Deepgram • San Francisco (CA)

On-site
USD 130,000 - 195,000
Embedded AI Engineer, On-Device Models
Embedded AI Engineer, On-Device Models

Devconnectplatform • United States

Remote
USD 219,000 - 274,000