AI Systems Research and Development Engineer – LLM Inference Systems & Optimization

📋 Description

• Design and develop high-performance LLM inference systems, spanning distributed serving, runtime
• Develop novel techniques to improve inference latency, generation speed, throughput, memory
• Explore advanced inference techniques including speculative and parallel decoding, prefill/decode
• Develop adaptive and intelligent inference systems that automatically optimize execution for new
• Apply AI-driven and AI-native approaches to systems engineering, including automated profiling
• Independently identify high-impact performance and systems problems, formulate hypotheses

🎯 Requirements

• Bachelor's degree in Computer Science, Computer Engineering, or related field; Master's degree or
• 5+ years of experience in AI systems research, GPU kernel networking, experience with CUDA, Triton
• Hands-on experience with modern LLM inference and serving frameworks such as vLLM, and TensorRT-LLM
• Strong understanding of LLM architectures and distributed inference systems
• Experience with performance-oriented libraries such as CUTLASS, cuBLAS, and related technologies
• Ability to work independently, design novel solving algorithms, and communicate findings