Principal Engineer, AI Serving Framework Architect (Software)

What this role involves

This Principal Engineer role focuses on architecting AI serving frameworks for large-scale systems. The position involves leading research on dynamic scheduling, memory optimization, and inference acceleration for multi-rack scale systems. Required expertise includes LLM inference stacks, vLLM, and proficiency in PyTorch, Python, and C++.

Skills this posting asks for

• ai serving framework
• large language model inference
• vllm
• pytorch
• python
• c++
• compute-capable memory
• hierarchical memory
• rag
• vector db
• ai agent
• knowledge-graph
• kvcache
• optimization algorithms
• multi-rack scale systems
• heterogeneous devices
• profiling
• dynamic scheduling
• memory optimization
• inference acceleration

Requirements

• 10 years of experience
• Level: principal
• Remote policy: onsite

From the employer’s posting

Please Note: To provide the best candidate experience amidst our high application volumes, each candidate is limited to 10 applications across all open jobs within a 6-month period.&nbsp; <span style=…