Embedded AI Engineer, On-Device Models

• Skills: Text to speech, Speech to text, Cloudflare, Machine Learning, C, Go, Rust, C++
• Experiences: Senior, Staff
• Employments: Full-time
• Locations: United States (Remote)

Description:

• Join Deepgram as an Embedded AI Engineer to optimize and run speech AI models on low-power devices.
• Work on model optimization, runtime code, and deployment for embedded and edge platforms.

Requirements:

• Experience with production systems on resource-constrained hardware (embedded systems, mobile, edge AI).
• Proficiency in C, C++, and/or Rust for performance-critical code in constrained environments.
• Hands-on experience with model optimization techniques (quantization, pruning, etc.).
• Familiarity with edge inference runtimes and vendor-specific NPU/DSP toolchains.
• Strong understanding of hardware-software interaction and inference performance.
• Experience in bare-metal or RTOS environments, embedded Linux, or microcontroller development.
• Strong communication skills and a builder mindset.

Benefits:

• Opportunity to work at the forefront of AI and hardware integration.
• Contribute to innovative voice AI solutions for consumer devices.