TinyML Engineer – Embedded AI for Edge Devices
Embedded Systems | Edge AI | Microcontrollers
Are you passionate about building intelligent systems that run on the edge?
We’re hiring a TinyML Engineer on behalf of our client, a cutting-edge tech company developing next-generation smart devices powered by embedded AI. In this role, you’ll join a collaborative remote team focused on deploying lightweight machine learning models on ultra-low-power microcontrollers.
What You’ll Do
- Design, optimize, and deploy ML models for embedded devices (e.g., STM32, nRF52, ESP32)
- Work closely with embedded firmware engineers to integrate models using frameworks like TensorFlow Lite for Microcontrollers, Edge Impulse, or CMSIS-NN
- Contribute to the end-to-end pipeline: from data collection and preprocessing to inference on constrained hardware
- Profile and debug memory, latency, and power consumption to ensure efficient model deployment
What We’re Looking For
- Strong experience with embedded C/C++, microcontroller development, and RTOS
- Hands-on experience with TinyML tools and techniques (e.g., model quantization, pruning, latency optimization)
- Experience with at least one ML framework (TensorFlow Lite Micro, PyTorch Mobile, etc.)
- Familiarity with sensors (audio, motion, vision) and signal processing
- Comfortable working in an agile, remote-first environment
Nice to Have
- Experience with Edge AI accelerators (e.g., Coral, Syntiant, Kneron)
- Background in DSP or low-power wireless communication
- Contributions to open-source TinyML projects