Systems Developer and Researcher (AI/LLM)

Location: Bellevue, WA, USA

Compensation: $236,000 – $330,000 per year

Company

Snowflake is a cloud-based data platform company powering the era of the agentic enterprise through AI-native engineering.

What you will do

• Design and develop high-performance LLM inference systems, including distributed serving and runtime systems.
• Develop novel techniques to improve inference latency, throughput, memory efficiency, and cost.
• Explore advanced inference techniques such as speculative decoding, KV-cache management, and adaptive parallelism.
• Apply AI-native approaches to systems engineering, including automated profiling and bottleneck identification.
• Develop strategies for multi-model serving, dynamic resource management, and model-system co-design.
• Collaborate with research, infrastructure, and product teams to deploy innovations into production.

Requirements

• Bachelor’s degree in Computer Science, Electrical Engineering, or related field (Master’s or PhD preferred).
• 5+ years of experience in LLM inference systems, distributed AI systems, GPU systems, or HPC.
• Strong understanding of modern LLM inference architectures and performance tradeoffs.
• Hands-on experience with frameworks like vLLM, SGLang, or TensorRT-LLM.
• Proficiency in GPU programming environments such as CUDA or Triton.
• Experience profiling system performance using tools like Nsight Systems or Nsight Compute.

Nice to have

• Experience using AI-native engineering approaches to accelerate software development and debugging.
• Experience with performance libraries like CUTLASS, cuBLAS, or cuDNN.

Culture & Benefits

• Opportunity to collaborate with world-class researchers and engineers from teams like DeepSpeed and vLLM.
• Focus on experimental mindset and rapid testing of emerging capabilities.
• Environment that encourages open-sourcing and publishing innovations in top-tier conferences.
• Commitment to redefining the future of work through AI-native engineering.