Optimize inference performance across the Akamai Inference Cloud
Collaborate closely with hardware performance engineers to deliver end-to-end optimization
Apply and evaluate quantization, distillation, and pruning techniques to optimize model performance while preserving accuracy
Design hardware-aware model placement and scheduling strategies to match models with optimal compute resources
Implement and tune speculative decoding, KV-cache optimization, and batching strategies to improve inference throughput and latency
Build benchmarking and profiling pipelines to measure model-layer performance across architectures, hardware, and serving configurations
Mentor and guide engineers on the team through code reviews, design discussions, and technical problem-solving
Collaborate with hardware performance engineers to identify and resolve end-to-end performance bottlenecks across the inference stack

12+ years of relevant experience with a Bachelor's or Master's degree in Computer Science, Machine Learning, or a related field
Possess hands-on experience optimizing LLM inference performance (quantization, speculative decoding, model compression, etc.)
Have a solid understanding of transformer architectures and how design choices impact latency, throughput, and accuracy
Possess experience with inference serving frameworks such as vLLM, TensorRT-LLM, Triton, or similar systems
Be proficient in Python and C++ with experience profiling and optimizing compute-intensive workloads
Have familiarity with hardware-aware optimization, including GPU/accelerator scheduling and memory management trade-offs

Principal Performance Engineer – Lead

Key skills