Lead Ai Inference Engineer Qvac 100% Remote Worldwide …, Avellaneda

About the role:You will own the inference backbone behind QVAC's local AI stack: the C++ systems layer that makes models run fast, reliably, and predictably on real user hardware. The role is centered on engineering quality at runtime level, including startup behavior, memory pressure, throughput/latency balance, and long-session stability. You will define and evolve the core abstractions that inference features depend on, so new capabilities can be added without sacrificing performance or maintainability. This is a role for someone who enjoys low-level problem solving, clear technical ownership, and building infrastructure that other teams trust in production. Your work directly enables private, on-device AI experiences and helps set the technical foundation for QVAC's next generation of peer-to-peer AI products.About the jobYou'll lead a cross‐functional pod that spans the full stack, from C++ inference engines to JavaScript applications. Your responsibility is to ensure that local AI capabilities ship reliably and perform well across devices. You'll balance hands‐on technical work with team coordination, guiding foundation and middleware engineers toward shared goals. This role is idóneo for someone who understands both the low‐level challenges of edge AI and the product‐facing needs of app developers, and wants to drive the delivery of cohesive, production‐ready local AI systems.ResponsibilitiesWork on deploying machine learning models to edge devices using the frameworks: llama.cpp, ggml, onnxCollaborate closely with researchers to assist in coding, training and transitioning models from research to production environmentsIntegrate AI features into existing products, enriching them with the latest advancements in machine learningManage a cross‐functional team (pod) made of middleware (JS), foundation (C++), QA and documentation engineers to produce high quality deliverablesRegularly assess, both qualitatively and quantitatively, our position in the market with regards to similar products or platformsLeverage the expertise of technical architects to ensure robust architectural choices and code qualityEnsure stable releases by following precise internal release processesQualificationsExcellent programming skills in C++Strong experience with Llama.cpp and ggml inference engines, which facilitates the deployment of models to specific GPU architecturesGood understanding of deep learning concepts and model architecturesExperience with transformers, LLMs, diffusion modelsDemonstrated ability to rapidly assimilate new technologies and techniquesExperience managing a small, specialized, cross‐functional team (pod) of 3‐5 peopleHas a genuine passion for building good products that improve people's livesA degree in Computer Science, AI, Machine Learning, or a related field, complemented by a solid track record in AI R&DBonus; points ifYou have extensive experience with JavaScript/TypeScriptYou understand the difficulties, nuances and importance of p2p technologyYou have experience with any of Vulkan, Metal and OpenCLYou have productionized models #J-*****-Ljbffr Postúlate en Kit Empleo: kitempleo.com.ar/empleo/qjadr