Senior NVIDIA LLM Inference Engineer

Deploy production LLMs remotely with NVIDIA inference technologies, GPU infrastructure, and Kubernetes-based environments for FullStack clients.

As a Senior AI Engineer, you will connect with United States clients through FullStack’s talent network. The work involves integrating with client teams on flexible, project-based development assignments. You will apply AI/ML engineering, software engineering, and machine learning infrastructure expertise to complex systems.

Key Responsibilities:

• Integrate directly into client engineering and design teams
• Deploy and self-host LLMs on production GPU infrastructure
• Serve and scale inference workloads across GPU clusters
• Operate Kubernetes environments using NVIDIA GPU Operator
• Implement guardrails for production LLM applications

Requirements:

• Five or more years of relevant professional experience
• Advanced English and a four-year college degree
• Hands-on NVIDIA NIM, NeMo, TensorRT-LLM, and Triton experience
• Understanding of LLM inference optimization and model serving
• Full-time work authorization without visa sponsorship

Apply NVIDIA inference, LLM deployment, and GPU operations expertise as a remote Senior AI Engineer with FullStack clients.