Search
Go
LLM Inference Engineer
Summary by AIEngineer.careers
LLM Inference Engineer is a LLM Engineer role (full-time). with Lattice. in REMOTE, WORLDWIDE. Imported listing (source: workflowza.zya.me). Apply on the employer's site (workflowza.zya.me).
Imported listing (source: workflowza.zya.me) · Apply on workflowza.zya.me
REMOTE · WORLDWIDE
—
Full-time
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from workflowza.zya.me
Join the NEAR AI team to build decentralized and confidential machine learning infrastructure for user-owned AI. This role focuses on high-performance LLM serving systems, optimizing throughput, latency, and cost for open-source LLMs. You will architect and maintain production-scale inference systems at global scale.
Responsibilities
- Architect and maintain production high-traffic LLM serving systems
- Optimize throughput, latency, and cost for leading open-source LLMs
Requirements
- Strong hands-on experience in LLM inference, with expertise debugging and optimizing major inference engines such as SGLang, vLLM, or TensorRT
- Deep knowledge of state-of-the-art GPU architectures and ability to exploit them using PyTorch, Triton, CuTe, CUDA, etc.
- Proven track record in designing and maintaining end-to-end high-traffic LLM serving systems
- Strong problem-solving skills and ability to communicate technical ideas clearly
Nice to Have
- Experience with Trusted Execution Environments (TEE)
- Active contributor to open-source LLM inference engines
Tech Stack
L
Lattice
San Francisco · US · 537+ employees
Lattice is a people management platform that helps companies streamline performance reviews, OKR and goal tracking, employee engagement surveys, and feedback loops. Its software is designed to align employees with company objectives and foster data-driven culture and management.
