Staff Software Engineer, Inference
- Hiring Organisation
- Humanloop
- Location
- London, UK
- Employment Type
- Full-time
oriented, with a bias towards flexibility and impactWillingness to pick up slack, even if it goes outside your job descriptionDesire to learn more about machine learning systems and infrastructureThrive in environments where technical excellence directly drives both business results and research breakthroughsCare about the societal impacts of your … workPreferred qualificationsSignificant experience with high-performance, large-scale distributed systemsExperience implementing and deploying machine learning systems at scaleExperience building load balancing, request routing, or traffic management systemsFamiliarity with LLM inference optimization, batching, and caching strategiesDeep experience operating Kubernetes and cloud infrastructure at scaleExperience with AI accelerator platforms (GPUs ...