AI Inference Engineer, QVAC at Tether

Confirmed open

Optimise C++ inference engines including llama.cpp and ggml for fast private AI on edge devices from Hanoi.

Tether

Location: Hanoi, Vietnam
Employment: fulltime_permanent
Work arrangement: remote
Technologies: JavaScript, C++

Role overview

The QVAC inference engineer works on the C++ runtime that runs local AI models without relying on cloud infrastructure. The role improves model loading, memory use and execution across edge hardware. The posting lists Hanoi, Vietnam.

Responsibilities

Deploy machine-learning models to edge devices with llama.cpp, ggml and relevant GPU frameworks.
Improve inference speed, memory use and runtime stability across hardware platforms.
Work with researchers to turn models into production implementations.
Integrate on-device AI features into existing products.

Qualifications

Strong C++ programming and practical llama.cpp or ggml inference-engine experience.
Experience with CUDA, Vulkan, Metal or OpenCL GPU frameworks.
Understanding of deep-learning models including transformers, LLMs and diffusion systems.
Computer science, AI or machine-learning degree and evidence of AI research and development.
Model fine-tuning, production inference, distributed systems or JavaScript are listed as bonus experience.

About Tether

Tether develops digital-token products, including USDT, alongside projects in peer-to-peer communications and AI. The employer describes a globally distributed remote team.

How to apply

Review the original posting and apply through the employer’s careers page.

View source and apply Apply directly

Source checked: 2026-09-29

Show what you can do

Build a free profile around your CV and real work. Share its link when you are ready. Applications for this role still go directly to the employer.

Build a free profile