Senior AI Inference Library Engineer - GPU-Optimized

LeoForce; San Francisco (CA); On-site; USD 175,000 - 250,000; Full time

Benefits offered by this job

Healthcare

Vision care

Dental

Equity in seed-stage startup

Job summary

LeoForce is seeking a Global Inference Library Engineer to design and optimize a high‑performance inference library for modern AI models. You will work across diverse compute architectures, squeezing maximum performance while integrating with model-serving infrastructure.

The role emphasizes deep knowledge of AI infrastructure, GPU programming, and low-level kernels, with exposure to frameworks like vLLM and TensorRT‑LLM. Join a technically focused startup building cutting-edge AI software.

Qualifications

• Strong experience building AI/ML infrastructure, inference systems, or HPC software.
• Strong programming experience with Python and C++, Rust, or similar systems languages.
• Hands-on experience with CUDA, ROCm, Triton, or similar GPU/accelerator programming technologies.
• Experience developing, integrating, or optimizing performance-critical compute kernels.

Responsibilities

• Build and maintain a high-performance inference library for modern AI models.
• Support inferencing across diverse compute architectures and accelerators.
• Profile, optimize, and tune performance-critical kernels and workflows.
• Collaborate on model-serving infrastructure and related tooling for scalability.

Skills

AI infrastructure

Python

C++

Rust

GPU programming

LLM inference

Performance profiling

Tools

vLLM

TensorRT-LLM

SGLang

CUDA

Triton

Job description

LeoForce is seeking a Global Inference Library Engineer to design and optimize a high‑performance inference library for modern AI models. You will work across diverse compute architectures, squeezing maximum performance while integrating with model-serving infrastructure.

The role emphasizes deep knowledge of AI infrastructure, GPU programming, and low-level kernels, with exposure to frameworks like vLLM and TensorRT‑LLM. Join a technically focused startup building cutting-edge AI software.