LLM Inference Runtime Engineer

INFERACT SINGAPORE PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Inferact is seeking an inference runtime engineer to push the boundaries of LLM and diffusion model serving. You will optimize how models execute across diverse hardware and architectures, and work at the core of vLLM to accelerate AI inference.

The role requires deep knowledge of transformer models, strong Python and PyTorch skills, and experience with LLM inference systems. You will read papers, implement techniques, and contribute robust, maintainable code to complex ML 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 and debug in complex ML codebases.

Responsibilities

• Push the boundaries of what's possible in LLM and diffusion model serving.
• Optimize how models execute across diverse hardware and architectures.
• Work at the core of vLLM to accelerate AI inference.

Skills

Python programming

PyTorch internals

Transformer architectures

LLM inference systems

Debug ML codebases

Education

Bachelor's degree in CS/Engineering

Tools

TensorRT-LLM

SGLang

TGI

Job description

Inferact is seeking an inference runtime engineer to push the boundaries of LLM and diffusion model serving. You will optimize how models execute across diverse hardware and architectures, and work at the core of vLLM to accelerate AI inference.

The role requires deep knowledge of transformer models, strong Python and PyTorch skills, and experience with LLM inference systems. You will read papers, implement techniques, and contribute robust, maintainable code to complex ML systems.