Embedded AI Engineer
Job Description
Hark is hiring an Embedded AI Engineer to take ownership of the full on-device AI stack and deliver AI on next-generation hardware.
Responsibilities
- Build data collection and ingestion pipelines for an embedded system using various sensors, scaled for high volume
- Partner with model teams to co-design model architectures that meet constraints for latency, memory, power, and bandwidth
- Collaborate with platform vendors to bring up toolchains, SDKs, and new accelerator capabilities for efficient model deployment and optimization
- Integrate ML inference into embedded firmware using C, C++, or Rust
- Profile and optimize memory usage, power consumption, and real-time performance
- Evaluate and select target silicon platforms (e.g., GPUs, NPUs) for next-generation on-device and edge deployment of a range of models
Requirements
- 5+ years of experience in machine learning engineering, including at least 2 years focused on embedded or edge ML
- Familiarity with embedded systems and CPU/DSP/NPU hardware architectures
- Hands-on experience with IMUs and other sensor types, including accelerometers, gyroscopes, and microphones
- Experience building sensor data collection pipelines
- Familiarity and experience with embedded ML runtimes such as TFLite, llamacpp, and QNN
- Experience optimizing models for deployment on microcontrollers and edge processors such as ARM Cortex-M/A and RISC-V, including DSPs
- Experience deploying workloads on NPUs or specialized accelerators for embedded systems
Technologies
- Languages: C, C++, Rust
- ML runtimes: TFLite, llamacpp, QNN
- Processors/accelerators: ARM Cortex-M, ARM Cortex-A, RISC-V, DSPs, GPUs, NPUs
- Sensors: IMUs, accelerometers, gyroscopes, microphones
Bonus Qualifications
- Experience with Audio/Voice/Vision models
- Experience with lightweight LLM models
- Understanding of edge AI model performance characteristics, including CNN, RNN, transformers, KV-cache behavior, and associated memory bandwidth needs
- Experience designing hybrid edge-LLM pipelines or integrating small language models on device
- Prior work on products in wearables, robotics, industrial sensing, or IoT
Compensation
- Base salary range (US): $200,000 - $450,000 annually for this full-time position
- Pay may vary based on job-related knowledge, skills, and experience
- Total compensation package may include additional components and benefits, shared if an offer is extended
Location: San Jose, CA (onsite)
Experience: 5+ years
Salary: USD 200,000 - 450,000 per yearly