Lead AI Inference Engineer (AI)

TL;DR

Lead AI Inference Engineer (AI): Leading a cross-functional pod, responsible for ensuring reliable shipping and performance of local AI capabilities across various devices. Focus on balancing hands-on technical work with team coordination to deliver cohesive, production-ready local AI systems.

Location: Remote

Company

hirify.global is a company building solutions that empower businesses to integrate reserve-backed tokens across blockchains, enabling secure and transparent digital transactions.

What you will do

• Deploy machine learning models to edge devices using frameworks like llama.cpp, ggml, and ONNX.
• Collaborate with researchers to assist in coding, training, and transitioning models from research to production.
• Integrate AI features into existing products, enhancing them with machine learning advancements.
• Manage a cross-functional pod of middleware, foundation, QA, and documentation engineers to produce high-quality deliverables.
• Assess the company's market position regarding similar products and platforms.
• Ensure stable releases by following precise internal release processes.

Requirements

• Excellent programming skills in C++.
• Strong experience with Llama.cpp and ggml inference engines.
• Good understanding of deep learning concepts and model architectures.
• Experience with transformers and LLMs.
• Demonstrated ability to rapidly assimilate new technologies and techniques.
• Experience managing a small, specialized, cross-functional team (pod) of 3-5 people.

Nice to have

• Extensive experience with Javascript/Typescript.
• Experience with AWS, containerization platforms, orchestration, and automated testing suites.
• Understanding of the difficulties, nuances, and importance of p2p technology.
• Experience with MLC, TVM, or similar frameworks.
• Experience with Vulkan, CUDA.
• Models that have been productionized.

Culture & Benefits

• Work remotely from anywhere in the world.
• Opportunity to collaborate with bright minds in the fintech space.
• Contribute to an innovative platform.