Member of technical staff (Inference)

H is a fast-growing AI startup seeking talented individuals to contribute to their inference stack, which powers their agent technology. The company values openness, collaboration, and a growth mindset, working with groundbreaking AI capabilities. They are looking for professionals who are passionate about building safe and responsible AI.

Requirements

• Develop scalable, low-latency and cost-effective inference pipelines
• Optimize model performance (memory usage, throughput, latency)
• Collaborate with H research teams on model architectures
• Review state-of-the-art papers to improve memory usage, throughput and latency
• Prioritize and implement state-of-the-art inference techniques
• Proficient in at least one of the following programming languages: Python, Rust or C/C++

Benefits

• Competitive salary
• Professional growth and learning opportunities
• Fun and collaborative team environment