AI Research Engineer (Kernel & Inference Optimization) - 100% Remote Worldwide
Core
Design and optimize model serving architectures and inference frameworks for advanced AI systems, focusing on high throughput, low latency, and efficient memory usage across diverse environments including edge and resource-constrained devices.
Role type
Senior IC AI Research Engineer (Kernel & Inference Optimization)
Builds
High-performance inference engines and optimized model serving pipelines for real-world applications
Domain
AI/ML, Mobile Computing, Edge Computing, Distributed Systems
Deliverable
production ML models
Required skills
GPU kernel development, Metal Shading Language (MSL), low-level kernel optimization, model serving architecture design, inference optimization techniques, distributed inference systems, Diffusion Models, Vision Transformers, model pruning, quantization, Flash attention, KV Cache, Speculative Decoding
Preferred skills
PhD in NLP/Machine Learning, publications in top-tier AI conferences, experience with mobile device inference
Technologies
Metal Shading Language, GPU clusters, Tensor Parallelism, Pipeline Parallelism, Expert Parallelism, Eagle (Speculative Decoding)
Responsibilities
Design and deploy state-of-the-art model serving architectures; Build, run, and monitor controlled inference tests in simulated and live environments; Identify and prepare high-quality test datasets for low-resource devices; Analyze computational efficiency and diagnose bottlenecks in serving pipelines; Integrate optimized frameworks into production pipelines for edge applications; Apply empirical research to overcome challenges in model serving
Seniority
Senior, hands-on IC