Qualifications
Your ResponsibilitiesDevelop the model serving platform, encompassing API, Control Plane, Billing, Monitoring, and distributed inference functionalities. Partner with ML researchers to integrate new multimodal models into existing production workflows. Write robust, maintainable code while adhering to strong testing and documentation practices. Deliver operational support to maintain high performance, availability, and reliability of production services. Assist in troubleshooting intricate issues across runtime, service, and GPU layers, collaborating closely with fellow engineers. Ideal Candidate ProfileBachelor's degree in Computer Science, Engineering, or a related technical discipline (or equivalent practical experience). A minimum of 3 years of software engineering experience, specifically in infrastructure or machine learning systems. Proficiency in programming languages such as C++, Python, Go, or Rust. Familiarity with Kubernetes and containerization techniques. Experience in building large-scale ML/MLOps infrastructure. Strong communication and collaboration skills, capable of working effectively across engineering and ML teams. Willingness to work from the office, contributing to a fast-paced and high-ownership team culture.
About the job
At Sciforium, we are at the forefront of AI infrastructure, dedicated to the development of advanced multimodal AI models and an innovative serving platform that emphasizes high efficiency. With substantial funding and direct collaboration from AMD, our team is rapidly expanding to create the complete stack for pioneering AI models and dynamic real-time applications.
Role Overview
This position provides a distinct opportunity to engage with the fundamental systems that drive Sciforium's multimodal AI models. You will play a crucial role in constructing the model serving platform, working with C++, Python, runtime execution, and distributed infrastructure to design a swift, dependable engine for real-time AI applications.
You will acquire practical experience in performance engineering, discover how large AI models are optimized and deployed at scale, and collaborate closely with ML researchers and seasoned systems engineers. If you thrive in low-level programming and are passionate about performance, this role offers both impactful contributions and significant growth opportunities.