D

Deepgram

Builds voice AI APIs for developers

Applied ML Engineer - Edge Devices

Applied Machine LearningUpdated on Nov 11
Full-timeRemote in USA$155k - $245k /yrRemote

About the Job

Requirements

  • Hands-on experience deploying machine-learning models to edge or non-NVIDIA hardware in production; cloud-only or GPU-only serving experience alone does not qualify.
  • Working knowledge of quantization and precision tradeoffs, including INT8, FP16, mixed precision, and calibration, and their effects on accuracy and latency on real targets.
  • Experience with at least one edge or vendor inference runtime and its conversion toolchain, such as ONNX Runtime, TFLite, ExecuTorch, OpenVINO, Qualcomm AI Engine, or a vendor NPU SDK.
  • Ability to modify models for a platform by reading and rewriting model graphs, swapping unsupported operators, and adjusting architecture parameters without breaking accuracy.
  • Strong Python and PyTorch skills, with production-quality engineering habits including tests, reproducibility, and rerunnable benchmarks.
  • Ability to build automation around model conversion and deployment.

Responsibilities

  • Port Deepgram speech models to non-NVIDIA and edge platforms, adapting model structure and parameters to run within the target's existing operator set, runtime, and kernels with minimal modification.
  • Own serving-side model decisions for edge targets, including quantization and precision choices, operator substitution, graph rewrites, and architecture adjustments to fit device constraints while maintaining accuracy and latency.
  • Validate each port on real hardware by building per-platform accuracy, latency, throughput, and memory benchmarks, and catching regressions before customers encounter them.
  • Build the deployment path for edge targets, including model packaging, conversion pipelines, versioning, and automated delivery, so deployment to new devices is repeatable.
  • Work with Embedded AI Engineers when standard kernels are insufficient by specifying model needs and adapting models to use the custom kernels they deliver.
  • Partner with platform and silicon vendors on runtimes and toolchains, translating expected model formats and operator conventions into working Deepgram deployments.
  • Feed edge constraints back to Research and Impeller so future models are easier to port, without taking on research or core productionization work.
  • As the team grows, take on adjacent edge-production concerns such as automated deployment, model security and integrity on customer hardware, and fleet-level observability.

Desired Qualifications

  • Experience with speech, audio, or streaming/real-time models.
  • Exposure to writing or reading low-level kernels such as CUDA, Metal, NEON, or vendor DSP code, sufficient to collaborate closely with embedded engineers.
  • Experience with model security or integrity on deployed devices, including signing, encrypted model storage, and safe updates.
  • Familiarity with several accelerator families, such as Qualcomm, Apple, ARM, Intel, AMD, or custom NPUs, and their quirks.
  • A track record of building internal tooling that measurably accelerated model porting or deployment.

About the Company

Deepgram

Builds voice AI APIs for developers

Deepgram builds speech software for developers and businesses that turn spoken conversations into text, generate voices, and run automated phone agents. Its Nova recognition models process live audio and recordings, with tools to identify speakers and recognize industry terms. Developers send audio or text through its APIs and receive transcripts, spoken responses, or extracted information that their applications use in customer service and other workflows. The company sells usage priced by audio minutes or generated characters, with prepaid credits and enterprise contracts for larger deployments. Deepgram was founded in 2015 and is headquartered in San Francisco, California, United States.

Company size
51-200
Company stage
Series C
Total funding
$233.3M
Headquarters
San Francisco, CA
Founded
2015

Recently Posted Jobs

Explore more opportunities at Deepgram

See more jobs