Applied ML Engineer - Edge Devices
Deepgram · USA - Remote
Applied AIremotesenior, staff$155k–$245k
At a glance
Highlights
- Adapt world-class speech models to run on edge servers and non-NVIDIA accelerators.
- Own repeatable deployment process getting adapted models onto real edge devices.
- Bridge model training and embedded teams to ship voice AI to customers.
Ideal candidate
Senior hands-on builder who has shipped ML to real edge hardware and loves adapting models to tough constraints. Pragmatic, autonomous, and motivated to ship to customers rather than publish.
Requirements
- Hands-on experience deploying ML models to edge or non-NVIDIA hardware in production
- Working knowledge of quantization and precision tradeoffs and impact on accuracy and latency
- Experience with an edge or vendor inference runtime and conversion toolchain
- Ability to modify model graphs, swap unsupported operators and adjust architecture parameters
- Strong Python and PyTorch with production-quality habits including tests and benchmarks
- Comfort building automation around model conversion and deployment
- Builder mindset and clear communication to scope ports and drive to measured results
- hiring process
- In interviews, expect to walk through a workflow you built and where you drew the line between AI and your own judgment.
Lab profile
About Deepgram
Real-time voice AI platform with speech models for conversational applications.
What they build
- Voice Agent Platform
- Speech models
- Real-time voice infrastructure
Known for
- Real-time speech processing
- Production-scale conversational voice AI
- Voice foundations and LLM research
Key facts
- 5,000+ organizations in production
Posted · Last seen