Senior Software Engineer - GPU Local AI Platforms

Job Description

The role involves optimizing LLM inference frameworks and model architectures for NVIDIA edge AI hardware. Responsibilities include developing inference recipes, characterizing multi-node behavior, and managing model validation workflows.

Requirements: Requires a degree in Computer Science or Engineering with over 12 years of experience in GPU computing and ML systems. Candidates must have strong C++/Python skills and hands-on experience with CUDA kernel development and container engineering.

Key Skills: GPU Computing, ML Systems, High-performance Inference, Python, C++, CUDA, Triton, LLM Inference, KV-cache Management, Continuous Batching, Quantization, Tensor Parallelism, Docker, OCI, NVIDIA Container Toolkit, Performance Analysis

Benefits: Equity, Comprehensive Benefits Package