Senior AI Inference Engineer

TL;DR

Senior AI Inference Engineer (AI Engineering): Develop and optimize the inference backbone for QVAC's local AI stack, focusing on C++ systems that enable fast, reliable, and stable model execution on user hardware with an accent on runtime quality, memory management, and performance. Focus on low-level problem solving, technical ownership, and building trusted infrastructure for private, on-device AI and peer-to-peer AI products.

Location: 100% Remote with team distributed globally; based in Bucharest, Romania.

Company

hirify.global is a leading fintech product company pioneering blockchain-based digital finance solutions, including the world’s most trusted stablecoin USDT and innovative AI and peer-to-peer technologies.

What you will do

• Own and engineer the inference backbone for QVAC's AI stack in C++ ensuring runtime quality and stability.
• Deploy machine learning models to edge devices using llama.cpp, ggml, and onnx frameworks.
• Collaborate closely with researchers to transition models from research to production.
• Integrate AI features into existing products to enhance machine learning capabilities.

Requirements

• Excellent programming skills in C++ with bonus experience in Javascript.
• Strong experience with llama.cpp and ggml inference engines for GPU-specific model deployment.
• Good understanding of deep learning concepts, transformers, LLMs, and diffusion models.
• Degree in Computer Science, AI, Machine Learning, or related field with proven AI R&D experience.
• Excellent English communication skills (C1+).

Nice to have

• Experience with Javascript/Typescript.
• Understanding of peer-to-peer technology challenges.
• Experience with Vulkan, Metal, and OpenCL.
• Productionized machine learning models.

Culture & Benefits

• Fully remote global team with flexible work environment.
• Opportunity to work on cutting-edge fintech and AI technologies.
• Collaborate with a diverse, innovative, and fast-growing company.