AI Inference Engineer (AI)

Location: Ukraine; remote flexibility is offered

Company

hirify.global is an AI engineering company building production systems for companies including Procter & Gamble and Shutterstock.

What you will do

• Deploy machine learning models to edge devices using llama.cpp and ggml.
• Integrate, evaluate, profile, and optimize AI inference pipelines for high-performance on-device execution.
• Collaborate with researchers on coding, training, and transitioning models from research to production.
• Integrate AI features into existing products using modern machine learning advancements.

Requirements

• 4+ years of professional experience with Modern C++17/20.
• Strong knowledge of memory management, multithreading, profiling, performance optimization, and low-level debugging.
• Experience developing in Linux environments and integrating machine learning models into production applications.
• Experience deploying and optimizing inference pipelines and profiling memory usage and latency.
• Understanding of Transformer architecture, LLMs, diffusion models, tokenization, attention mechanisms, KV cache, quantization, model conversion, and deployment.
• Practical experience with LLM deployment, computer vision, OCR, multimodal, speech, or image generation models.

Nice to have

• Experience with llama.cpp, ggml, ONNX Runtime, TensorRT, TensorRT-LLM, OpenVINO, MLC LLM, ExecuTorch, or TVM.
• CUDA, Vulkan Compute, Metal, OpenCL, TypeScript, or Python.
• Experience contributing to open-source AI infrastructure projects.
• Experience evaluating new models and integrating them into existing products.

Culture & Benefits

• Remote work flexibility.
• Competitive compensation with medical, wellness, and learning benefits.
• English classes, professional development, well-being support, and career progression opportunities.
• Ownership of problem-solving initiatives and support for responsible experimentation.
• Regular meetups, tech talks, and collaborative support from colleagues.