AI Research Engineer optimizing model compression and inference for edge deployment.
You'll work on optimizing AI model compression and quantization techniques for edge deployment in a senior-level permanent role. The position involves developing GPU kernels and leveraging frameworks like PyTorch and TensorFlow, along with Metal Shading Language and ONNX for efficient inference. You'll apply expertise in tensor and pipeline parallelism to reduce model size and computational requirements. This is a full-time remote position available worldwide, conducted in English.
Membership is €29/month, cancel anytime: every rate, every original listing link, and a daily alert for roles matching your filters.
Found at a specialist agency · listed 22 July 2026 · InsideJobs links you to the original posting.