AI Inference Engineer QVAC (100% Remote)

About the role

Tether is looking for an AI Inference Engineer for its QVAC project, a 100% remote position open worldwide. You will own the inference backbone of QVAC's local AI stack: the C++ systems layer that makes models run fast, reliably and predictably on real user hardware. The role focuses on engineering quality at runtime, including startup behavior, memory pressure, throughput/latency balance and long-session stability, and defines the core abstractions that inference features depend on.

Key responsibilities

• Work on the C++ layer that powers local AI, porting and enhancing inference engines such as llama.cpp or similar to run efficiently on edge devices
• Deploy machine learning models to edge devices using llama.cpp and ggml
• Collaborate closely with researchers to help code, train and transition models from research to production environments
• Integrate AI features into existing products

Required profile

• Degree in Computer Science, AI, Machine Learning or a related field, with a solid track record in AI R&D
• Excellent English communication skills
• Ability to rapidly assimilate new technologies and techniques

Required skills

• Strong C++ programming skills
• Strong experience with Llama.cpp and ggml inference engines
• Experience with a GPU framework such as CUDA, Vulkan, Metal or OpenCL
• Understanding of deep learning concepts, transformers, LLMs and diffusion models
• Bonus: training or fine-tuning of LLMs, productionized models, research experience in new architectures, distributed systems, and JavaScript