Applied ML Engineer - Edge Devices
Deepgram · USA
About this role
## Applied ML Engineer - Edge Devices ### Company Overview Deepgram is the leading platform underpinning the Voice AI economy, offering real-time APIs for speech-to-text (STT), text-to-speech (TTS), and production-grade voice agents at scale. With voice-native foundation models available via cloud APIs or self-hosted/on-premises software, Deepgram is known for accuracy, low latency, and cost efficiency. ### About the Role Deepgram’s speech models run at scale on NVIDIA GPUs today. Customers increasingly need those same models on hardware Deepgram doesn’t control—non-NVIDIA accelerators, edge servers, and embedded platforms with their own inference runtimes, operator sets, and constraints. As an **Applied ML Engineer** on the **Partner Platform Engineering** team, you’ll adapt Deepgram models to run correctly and efficiently within each target platform’s existing runtime and kernel paradigm. This is **applied ML for edge deployment**—not a research role and not a cloud-serving role. ### What You’ll Do - **Port Deepgram speech models** to non-NVIDIA and edge platforms by adapting model structure/parameters to fit the target’s operator set, runtime, and kernels with minimal modification. - Own **serving-side model decisions** for edge targets, including quantization/precision choices, operator substitution, graph rewrites, and architecture tweaks to meet device constraints while maintaining accuracy and latency. - **Validate on real hardware**: build accuracy, latency, throughput, and memory benchmarks per platform; catch regressions before customers do. - Build the **deployment path** for edge targets: model packaging, conversion pipelines, versioning, and automated delivery so new device support is repeatable. - Collaborate with **Embedded AI Engineers** when standard kernels aren’t sufficient—specify model needs and integrate custom kernels. - Partner with **platform and silicon vendors** on runtimes/toolchains to translate expected model formats and operator conventions into working Deepgram deployments. - Feed edge constraints back to **Research and Impeller** to make future models easier to port. - As the team grows, take on adjacent edge production concerns such as **automated deployment, model security/integrity**, and **fleet-level observability**. ### You’ll Love This Role If - You’ve fought to get models running on hardware not built for them—and want to do it across many platforms. - You prefer adapting the model to the hardware (and know when that’s the right call). - You care about device performance metrics, not just notebook results. - You enjoy bridging the gap between kernel/embedded engineering and model teams. - You want to **ship to customers**, not publish. ### Required Qualifications - **Hands-on experience deploying ML models to edge or non-NVIDIA hardware in production** (required). Cloud-only or GPU-only serving experience alone does not qualify. - Working knowledge of **quantization and precision tradeoffs** (e.g., INT8, FP16, mixed precision, calibration) and their impact on real targets. - Experience with at least one **edge/vendor inference runtime** and its conversion toolchain (e.g., ONNX Runtime, TFLite, ExecuTorch, OpenVINO, Qualcomm AI Engine, or a vendor NPU SDK). - Ability to **modify models to fit a platform**: read/rewrite model graphs, swap unsupported operators, adjust architecture parameters without breaking accuracy. - Strong **Python and PyTorch** with production-quality engineering habits
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.