Machine Learning Engineer- Inference Optimization | Experienced Hire
Core
Design, build, and optimize low-latency inference systems for production machine learning workloads, focusing on transformer-style architectures and GPU performance.
Role type
Senior IC machine learning engineer (inference optimization)
Builds
High-performance model serving systems for production ML workloads
Domain
Machine Learning / Systems Engineering / GPU Computing
Deliverable
production ML models
Required skills
Python, C/C++, Rust, Go, PyTorch, low-latency system design, GPU memory management, profiling tools, batching strategies, precision tradeoffs
Preferred skills
Model quantization, pruning, distillation, operator fusion, graph lowering, CUDA, Triton, ROCm, Kubernetes, GPU cluster management
Technologies
PyTorch, CUDA, Triton, ROCm, PTX, CuTe, CUTLASS, FlashInfer, Kubernetes
Responsibilities
Design and optimize low-latency inference systems; Profile model inference pipelines; Evaluate and tune inference runtime systems; Build benchmarking and profiling tools; Debug performance issues involving GPU/CPU coordination; Collaborate on custom operators or kernel-level optimization
Seniority
Senior, hands-on IC
