LLM Inference Engineer: GPU-Optimized Serving

Energy Jobline ZR; San Francisco (CA); On-site; USD 180,000 - 300,000; Full time

Job summary

GMI Cloud in San Francisco is building the leading inference optimization solution and the most advanced token platform in the global token market — and we are hiring world-class Machine Learning Engineers to make GMI the new industry benchmark for LLM serving performance, cost efficiency, and production reliability.

GMI Cloud invites engineers to work on frontier research across quantization, speculative decoding, KV cache & memory management, and PD disaggregation, partnering with platform,

Qualifications

• Experience optimizing large-scale LLM inference in production.
• Proven track record reducing latency and boosting throughput.
• Contributions to open-source inference projects.

Responsibilities

• Drive frontier research in LLM inference optimization.
• Develop optimization strategies for large-scale serving across model execution, runtime systems, and production inference platforms.

Skills

LLM inference systems

inference metrics

serving stacks

GPU-based inference

Speculative decoding

Quantization

PD disaggregation

KV cache & memory

Open-source contributions

Technical publishing

Education

PhD in related areas

Tools

SGLang

vLLM

TensorRT-LLM

NVIDIA Dynamo

Triton

Job description

GMI Cloud in San Francisco is building the leading inference optimization solution and the most advanced token platform in the global token market — and we are hiring world-class Machine Learning Engineers to make GMI the new industry benchmark for LLM serving performance, cost efficiency, and production reliability.

GMI Cloud invites engineers to work on frontier research across quantization, speculative decoding, KV cache & memory management, and PD disaggregation, partnering with platform,