Remote Inference Runtime Engineer for LLM & Multimodal AI

Inferact; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Visa sponsorship

Health coverage

Fully remote

Job summary

Inferact is seeking an inference runtime engineer to advance LLM and diffusion model serving. You will optimize how models execute across diverse hardware, shaping the core of vLLM and enabling faster AI inference.

This remote role embraces flexible timezones with Pacific overlap for critical syncs, and compensation includes salary plus equity. The ideal candidate will have deep knowledge of transformer models, strong Python/PyTorch skills, and hands-on experience with LLM inference systems.

Qualifications

• Bachelor’s degree or equivalent experience in computer science, engineering, or similar.
• Deep understanding of transformer architectures and their variants.
• Strong programming skills in Python with experience in PyTorch internals.
• Experience with LLM inference systems (vLLM, TensorRT-LLM, SGLang, TGI).
• Ability to read and implement model architectures and inference techniques from research papers.
• Demonstrate the ability to contribute performant and maintainable code in complex ML codebases.

Skills

Transformer architectures

Python

PyTorch internals

LLM inference systems

Read and implement research papers

performant code in ML

Education

Bachelor’s degree or equivalent experience

Tools

vLLM

TensorRT-LLM

SGLang

TGI

Job description

Inferact is seeking an inference runtime engineer to advance LLM and diffusion model serving. You will optimize how models execute across diverse hardware, shaping the core of vLLM and enabling faster AI inference.

This remote role embraces flexible timezones with Pacific overlap for critical syncs, and compensation includes salary plus equity. The ideal candidate will have deep knowledge of transformer models, strong Python/PyTorch skills, and hands-on experience with LLM inference systems.