Senior System Software Engineer - Dynamo-Triton Inference Server
Core
Develop world-class GPU-accelerated AI inference serving software to unify the Triton Inference Server and NVIDIA Dynamo stacks for LLM and non-LLM workloads.
Role type
Senior System Software Engineer (AI Inference Platform)
Builds
High-performance AI inference platform serving Large Language Models (LLM) and non-LLM workloads
Domain
Deep Learning / GPU Computing / Distributed Systems
Deliverable
production ML models
Required skills
Rust, C++, Python, high-scale distributed systems, ML systems, performance analysis, test design, debugging, software design
Preferred skills
AI frameworks (TensorRT, PyTorch, ONNX, OpenVINO, vLLM, TRT-LLM), GPU memory management, cache management, high-performance networking, open source contribution
Technologies
Rust, C++, Python, TensorRT, PyTorch, ONNX, OpenVINO, vLLM, TRT-LLM, Triton Inference Server, NVIDIA Dynamo
Responsibilities
Develop GPU-accelerated AI inference serving software; Contribute to feature development and drive customer adoption; Drive convergence of Triton and Dynamo stacks; Balance objectives of robust production deployment, throughput/latency optimization, and next-gen technology adoption
Seniority
Senior, hands-on IC
