Edge ML Engineer - Deploy ML on Non-NVIDIA Platforms

Fdetimes; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Deepgram is seeking an Applied ML Engineer for the Partner Platform Engineering team. You will port Deepgram speech models to non-NVIDIA and edge platforms, adapting models to run within target kernels and operator sets, while maintaining accuracy and latency.

You’ll own deployment paths, validate on real hardware, and collaborate with Embedded AI Engineers to integrate custom kernels. This role focuses on applied ML for edge deployment, not research or cloud-serving, offering opportunities to

Qualifications

• Hands-on experience deploying ML models to edge or non-NVIDIA hardware in production.
• Working knowledge of quantization and precision tradeoffs (INT8, FP16, mixed precision) and their impact on accuracy/latency.
• Experience with at least one edge or vendor inference runtime (ONNX Runtime, TFLite, ExecuTorch, OpenVINO, Qualcomm AI Engine, or vendor NPU SDK).
• Ability to modify a model to fit a platform: rewrite graphs, swap operators, adjust architecture without breaking accuracy.
• Strong Python and PyTorch, and production-quality engineering habits (tests, reproducibility, benchmarks).
• Comfort building automation around model conversion and deployment.
• Builder mindset and clear communication to scope ports on unfamiliar platforms.

Responsibilities

• Port Deepgram speech models to non-NVIDIA and edge platforms, adapting to target operator sets and kernels with minimal modification.
• Own serving-side model decisions for edge targets: quantization, precision, operator substitution, graph rewrites, and architecture tweaks.
• Validate port on real hardware: build accuracy, latency, throughput, and memory benchmarks; catch regressions before customers.
• Build deployment path for edge targets: packaging, conversion pipelines, versioning, automated delivery for repeatable deployments.
• Collaborate with Embedded AI Engineers when standard kernels aren’t enough; specify needs and integrate custom kernels.
• Partner with platform and silicon vendors on runtimes/toolchains to convert models for Deepgram deployment.
• Provide feedback to Research/Impeller to ease future porting efforts.
• As team grows, handle adjacent production concerns at edge: automated deployment, security, and fleet observability.

Skills

Edge deployment

Python

PyTorch

Model conversion automation

Quantization & precision

Job description

Deepgram is seeking an Applied ML Engineer for the Partner Platform Engineering team. You will port Deepgram speech models to non-NVIDIA and edge platforms, adapting models to run within target kernels and operator sets, while maintaining accuracy and latency.

You’ll own deployment paths, validate on real hardware, and collaborate with Embedded AI Engineers to integrate custom kernels. This role focuses on applied ML for edge deployment, not research or cloud-serving, offering opportunities to