Remote ML Inference Infrastructure Engineer

United States Digital Space LLC; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

United States Digital Space LLC is seeking an experienced engineer to optimize model serving pipelines using vLLM, TensorRT, and Triton. You will own the inference layer and drive benchmarking to ensure low latency and high throughput at scale.

You'll implement quantization strategies (FP8, AWQ, GPTQ) and build eval harnesses and InferenceBench-style tests to compare against industry standards. This is a remote, full-time role.

Qualifications

• Shipped at least one production inference stack on H100s or A100s.
• Familiar with vLLM and large model serving.
• Strong knowledge of quantization and eval methodologies.

Responsibilities

• Own the serving stack per workload and optimize latency and throughput.
• Develop quantization approaches and eval harnesses.
• Create InferenceBench-style benchmarks to compare stacks.

Skills

vLLM

TensorRT

Triton

Benchmarking

FP8 quantization

GPTQ

InferenceBench

Job description

United States Digital Space LLC is seeking an experienced engineer to optimize model serving pipelines using vLLM, TensorRT, and Triton. You will own the inference layer and drive benchmarking to ensure low latency and high throughput at scale.

You'll implement quantization strategies (FP8, AWQ, GPTQ) and build eval harnesses and InferenceBench-style tests to compare against industry standards. This is a remote, full-time role.