Technical Staff Member (Inference) - Paris
H
About H:At H, our mission is to redefine the frontiers of superintelligence through agentic AI. By automating intricate, multi-step tasks that are traditionally handled by humans, our AI agents aim to unlock the full potential of human capabilities.We are on the lookout for the brightest minds in AI, individuals who are committed to developing technology that is both safe and responsible, whilst pushing the boundaries of disruptive agentic capabilities. Our culture thrives on openness, continuous learning, and collaborative efforts, where every team member’s input is valued.About the Team: The Inference team is dedicated to developing and refining the inference stack that powers our H-models, which drive our agent technology. Our focus lies in optimizing hardware utilization to achieve high throughput, low latency, and cost-effectiveness, ensuring a smooth user experience.Key Responsibilities:Design and implement scalable, low-latency, and cost-effective inference pipelines.Enhance model performance through optimization of memory usage, throughput, and latency, employing advanced techniques such as distributed computing, model compression, quantization, and caching.Create specialized GPU kernels for critical performance tasks, including attention mechanisms and matrix multiplications.Collaborate with H's research teams to refine model architectures and improve inference efficiency.Stay abreast of cutting-edge research by reviewing state-of-the-art papers to enhance memory usage, throughput, and latency (e.g., Flash attention, Paged Attention, Continuous batching).Prioritize and deploy the latest inference techniques.Requirements:Technical Skills:Master's or PhD in Computer Science, Machine Learning, or a related discipline.Proficiency in one or more programming languages: Python, Rust, or C/C++.Experience with GPU programming frameworks such as CUDA, Open AI Triton, or Metal.Familiarity with model compression and quantization techniques.Soft Skills:A collaborative spirit and the ability to excel in dynamic, multidisciplinary teams.Excellent communication and presentation abilities.A strong desire to tackle new challenges.
Apr 14, 2026