Senior/Staff System Research Engineer – LLM Inference Optimization

What you'll do

• Develop high-performance inference systems and techniques to improve latency, throughput, memory efficiency, scalability, and cost.
• Build adaptive systems that profile workloads, identify bottlenecks, and select execution strategies across models, hardware, and deployments.
• Profile and optimize end-to-end inference, including distributed execution and GPU kernels, and collaborate to deploy innovations in production.

What they ask for

• Bachelor’s degree in Computer Science, Electrical Engineering, or a related field.
• 5+ years of experience in one or more of: LLM inference systems, distributed AI systems, GPU systems, or high-performance computing.
• Experience with LLM inference frameworks, inference-runtime optimization, GPU programming environments, and performance profiling tools.
• Strong understanding of LLM inference architectures, GPU systems, and end-to-end performance tradeoffs; able to independently identify problems and drive solutions.

Nice to have

• A Master’s degree or PhD.
• Experience using AI-native engineering approaches to accelerate development, experimentation, debugging, optimization, or system adaptation.

Tools

vLLM, SGLang, TensorRT-LLM, CUDA, Triton, CUTLASS, cuBLAS, Nsight Systems

AI focus

Optimizes LLM inference and develops AI-driven systems that automate profiling, bottleneck identification, configuration search, code generation, strategy selection, debugging, and performance tuning.