LLM Inference Optimization Engineer — Frontier Performance

NLP PEOPLE; Sonoma (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

NLP PEOPLE is seeking world-class Machine Learning Engineers to develop leading inference optimization solutions. The role involves driving research and executing advanced LLM techniques to establish industry benchmarks.

Candidates should have hands-on experience with GPU optimization and knowledge of serving technologies. A collaborative spirit and the ability to publish results are essential. This position represents an exciting opportunity to push the boundaries in AI technology.

Qualifications

• Experienced with LLM inference systems and modern GPU optimization.
• Familiar with inference metrics and tradeoffs.
• Experience with frameworks for large-scale serving.

Responsibilities

• Drive research in LLM inference optimization across focus tracks.
• Develop optimization strategies for large-scale model serving.
• Engage with the open-source community.

Skills

LLM inference optimization

GPU performance optimization

Quantization

Speculative decoding

Collaboration with teams

Education

2+ years of relevant experience or PhD

Tools

SGLang

vLLM

TensorRT-LLM

NVIDIA Dynamo

Triton

Job description

NLP PEOPLE is seeking world-class Machine Learning Engineers to develop leading inference optimization solutions. The role involves driving research and executing advanced LLM techniques to establish industry benchmarks.

Candidates should have hands-on experience with GPU optimization and knowledge of serving technologies. A collaborative spirit and the ability to publish results are essential. This position represents an exciting opportunity to push the boundaries in AI technology.