AI Inference Engineer QVAC (100% remote Worldwide)
Core
Own the inference backbone for QVAC's local AI stack, building C++ systems layers to run models fast and reliably on real user hardware.
Role type
Senior IC AI inference engineer (edge systems)
Builds
Local AI inference engines and runtime infrastructure for edge devices
Domain
Fintech / Edge AI / Embedded Systems
Deliverable
production ML models
Required skills
C++, llama.cpp, ggml, GPU frameworks (CUDA, Vulkan, Metal, OpenCL), deep learning concepts, transformers, LLMs, Diffusion models
Preferred skills
LLM training/fine-tuning, model productionization, new model architecture research, distributed systems, JavaScript
Technologies
llama.cpp, ggml, CUDA, Vulkan, Metal, OpenCL
Responsibilities
Deploy machine learning models to edge devices using llama.cpp and ggml; Collaborate with researchers to transition models from research to production; Integrate AI features into existing products; Optimize runtime performance for memory pressure, throughput, and latency
Seniority
Senior, hands-on IC