Machine Learning Engineer, Edge AI

We are looking for a Machine Learning Engineer, Edge AI to lead the integration and control of our next-generation AI accelerators. As our products evolve to include dedicated neural network hardware, the challenge shifts from pure algorithm implementation to complex hardware orchestration.

This role is about more than just writing kernels; it’s about defining the firmware layer that sits between high-level AI frameworks and our custom silicon. You will be responsible for how our DSPs manage, schedule, and feed data to these accelerators. We need a veteran who can look at a PyTorch model and determine the best way to tile memory, manage DMA transfers, and synchronize processing to ensure we hit our ultra-low-power targets while maximizing throughput. You will also be the primary technical voice influencing our future hardware specs to ensure our accelerators are actually "firmware-friendly."

What You Will Do

• Lead research and development efforts in edge AI and embedded machine learning.
• Design, train, evaluate, optimize, and deploy machine learning models spanning applications from low-power 1D sensor processing through high-dimensional sensing systems such as ultrasonic arrays.
• Investigate and develop novel architectures for constrained edge deployments, balancing performance, power, latency, and memory requirements.
• Optimize AI workloads through techniques such as quantization, pruning, graph optimization, kernel acceleration, and hardware-aware training.
• Deploy models across a variety of hardware platforms, including onsemi solutions and third-party edge AI hardware.
• Stay current with advances in machine learning research and translate promising techniques into scalable, production-ready products.
• Work closely with hardware, firmware, and software teams to co-design AI solutions that maximize efficiency, performance, and scalability on resource-constrained edge platforms

What You’ll Need

• Strong Python, PyTorch and ONNX experience developing, training, evaluating, and deploying machine learning models.
• Deep understanding of modern AI architectures including CNNs, Transformers, state-space models, and other emerging neural network approaches.
• Experience optimizing, deploying and debugging models across a wide spectrum of edge devices, from ultra-constrained microcontrollers and DSPs to high-performance AI accelerators and GPUs.
• Experience developing machine learning solutions for one or more sensing domains, including time-series signals, audio, computer vision, or ultrasonic sensing.
• Hands-on experience with model compression and deployment techniques such as quantization, pruning, graph optimization, and operator/kernel optimization.
• Practical experience translating research concepts into production-quality systems.
• Strong understanding of model performance tradeoffs involving latency, memory footprint, power consumption, and accuracy.
• 4+ years of industry and/or academic experience in machine learning research, model development, or AI systems engineering.

Nice to Have

• CUDA development and GPU optimization experience.
• Experience with TensorRT, ONNX Runtime, TVN, IREE, or similar inference frameworks.
• Experience with TinyML, embedded inference runtimes, or DSP programming.
• Familiarity with multimodal AI systems.

onsemi is excited to share the base salary range for this position i$120,000 - $170,000 exclusive of fringe benefits or potential bonuses. The final pay rate for the successful candidate will depend on geographic location, skills, education, experience, and/or consideration of internal equity of our current team members. We also offer a competitive benefits package