Embedded AI Engineer
Job Description
Hark is hiring an Embedded AI Engineer in San Jose, CA (onsite) to take ownership of the end-to-end on-device AI stack. The role spans sensor data ingestion, model development and optimization, and deployment of ML inference into embedded firmware.
Responsibilities
- Build data collection and ingestion pipelines for an embedded system using multiple sensor inputs at scale
- Partner with model teams to co-design model architectures that meet latency, memory, power, and bandwidth requirements
- Coordinate with platform vendors to stand up toolchains and SDKs, including bring-up of new accelerator hardware, to support efficient model deployment and optimization
- Integrate ML inference into embedded firmware implemented in C, C++, or Rust
- Profile and optimize memory usage, power consumption, and real-time performance characteristics
- Evaluate and select silicon platforms, including GPUs and NPUs, for next-generation on-device and edge deployments across 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 with embedded ML runtimes such as TFLite, llamacpp, and QNN
- Experience optimizing models for deployment on microcontrollers and edge processors including ARM Cortex-M/A, RISC-V, and DSPs
- Experience deploying workloads on NPUs or other specialized accelerators for embedded systems
Technologies
- C, C++, Rust
- TFLite, llamacpp, QNN
- ARM Cortex-M, ARM Cortex-A, RISC-V, DSPs
- GPUs, NPUs
- 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 CNNs, RNNs, transformers, KV-cache behavior, and 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
- US base salary range for this full-time position: $200,000 - $450,000 annually
- Compensation may vary based on job-related knowledge, skills, and experience
- Total compensation package may include additional components or benefits, which will be shared if an employment offer is extended