Applied ML Engineer - Edge Devices
AI · 3 roles open in software and data
- Location: Remote (US)
- Pay: $155k–$245k a year
- Posted: Posted
About the role
The team adapts Deepgram's speech models to run on diverse edge hardware. The engineer modifies model structures, adjusts parameters, and optimizes performance for specific device constraints. This role involves validating accuracy and latency on real hardware and building repeatable deployment processes.
Our summary of the posting; the original is on the Deepgram careers page.
What the posting requires
- Required
- Quantization
- ONNX Runtime
- Model modification
- Python
- Engineering habits
- Automation
- Precision tradeoffs
- TFLite
- Model graphs
- PyTorch
- Preferred
- Low-level kernels
- Model security
- Accelerator families
- CUDA
- Model integrity
- Qualcomm
These tags are our reading of the posting. They can miss something; the original posting is the reference.
Do you qualify?
Each requirement checked against your resume, in about a minute. No account. Your resume is deleted when the verdict appears.