Embedded AI Engineer, On-Device Models

Job not on LinkedIn

🔥 0 minutes ago

🇺🇸 United States – Remote

💵 $219.3k - $274.1k / year

⏰ Full Time

🟡 Mid-level

🟠 Senior

⚙️ Systems Engineer

🦅 H1B Visa Sponsor

This company has sponsored H1B visas in the past.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Deepgram

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2015

🤖 Artificial Intelligence

☁️ SaaS

🔌 API

💰 $47M Series B on 2022-11

Artificial Intelligence • SaaS • API

Deepgram is a leading voice AI company that provides powerful APIs for speech-to-text, text-to-speech, and language understanding applications. Their platform enables developers to build sophisticated voice AI solutions for use cases such as contact centers, medical transcription, conversational AI, and more. Known for unmatched accuracy, speed, and cost-effectiveness, Deepgram's technology is trusted by top enterprises and startups worldwide. By offering real-time and highly accurate transcription capabilities, Deepgram helps businesses gain insights from voice data, making it an essential tool for transforming voice interactions.

📋 Description

• Take Deepgram's Speech and Conversational models and get them running on embedded and low-power consumer hardware — defining the architecture for on-device, real-time inference across a diverse range of processors and accelerators. • Optimize models for constrained targets through quantization, pruning, distillation, operator fusion, and architecture-specific compilation to meet strict latency, memory, power, and thermal budgets. • Write and optimize performance-critical runtime code (C, C++, and/or Rust) for embedded environments, including bare-metal and real-time operating systems such as FreeRTOS and Zephyr. • Integrate with industry-standard edge inference runtimes and vendor NPU/DSP toolchains, mapping model graphs efficiently onto on-device accelerators and CPU/GPU/NPU heterogeneity. • Build the on-device runtime plumbing: model packaging, deployment pipelines, over-the-air update mechanisms, and lightweight telemetry for devices operating with limited or intermittent connectivity. • Establish repeatable benchmarking and validation across target hardware — measuring latency, accuracy, power consumption, memory footprint, and resource utilization — and catch regressions before they ship. • Partner with silicon and device vendors on SDK integration and performance tuning, getting our models to run efficiently on new chipsets and reference platforms. • Collaborate with Research and Engine teams to influence model architectures toward edge-friendly designs from the start, reducing the optimization burden at deployment time.

🎯 Requirements

• Experience delivering production systems on resource-constrained hardware — embedded systems, mobile, edge AI, or small low-power devices. • Strong proficiency in C, C++, and/or Rust, with experience writing performance-critical code for constrained environments. • Hands-on experience with model optimization for on-device deployment, including quantization, pruning, knowledge distillation, or architecture-specific compilation. • Familiarity with edge inference runtimes (e.g., ONNX Runtime, TensorRT, TFLite, ExecuTorch) and/or vendor-specific NPU/DSP toolchains. • A strong understanding of hardware-software interaction — CPU/GPU/NPU/DSP architectures, memory hierarchies, fixed-point/integer arithmetic, and power management — and how they affect inference performance. • Experience working close to the metal: bare-metal or RTOS environments (e.g., FreeRTOS, Zephyr), embedded Linux, or microcontroller and edge SoC development. • Strong communication skills and a builder mindset — you can scope an ambiguous optimization problem, drive it to a measurable result, and explain the tradeoffs clearly.

🏖️ Benefits

• Offers Equity • Offers Bonus • 10% Annual Bonus