GPU MLOps Engineer for GenAI Inference & Kernel Ops

Mercor; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Cincinnatus LLC is seeking an MLOps Engineer to help build foundational AI models within a leading AI lab environment. The role focuses on GPU kernel work, performance profiling, debugging distributed workloads, and serving large language models at scale.

The position is a 40-hour full-time engagement with W-2 employment through Cincinnatus LLC, offering placement at a top AI lab and collaboration with researchers on frontier AI systems.

Qualifications

• 2+ years of hands-on professional experience in ML systems, ML infrastructure, model serving, or GPU and accelerator performance engineering.
• Hands-on work with GPU kernels, performance profiling, distributed workloads, or serving LLMs at scale.

Responsibilities

• Design challenging, domain-relevant tasks across GPU kernels, performance profiling, debugging, and inference serving.
• Guide research and engineering teams to close knowledge gaps and improve AI model performance on training and serving infra.
• Evaluate MLOps and ML systems tasks with clear, written technical feedback for reviewers.
• Develop guidelines and rubrics covering kernel optimization, profiler interpretation, and latency trade-offs.
• Collaborate with subject matter experts to keep training data consistent and accurate.

Skills

ML systems

ML infrastructure

GPU kernels

performance profiling

distributed workloads

model serving

JAX/PyTorch

Tools

CUDA

Triton

Kineto

Nsight

XLA

Job description

Cincinnatus LLC is seeking an MLOps Engineer to help build foundational AI models within a leading AI lab environment. The role focuses on GPU kernel work, performance profiling, debugging distributed workloads, and serving large language models at scale.

The position is a 40-hour full-time engagement with W-2 employment through Cincinnatus LLC, offering placement at a top AI lab and collaboration with researchers on frontier AI systems.