Senior AI Serving Engineer, Backend

This role involves building the model serving platform for Sciforium's multimodal AI models, working across C++, Python, runtime execution, and distributed infrastructure. Responsibilities include API, Control Plane, Billing, Monitoring, and distributed inference features. Collaborate with ML researchers, write reliable code, provide operational support, and troubleshoot complex issues across runtime, service, and GPU layers.

Bachelor's in CS or equivalent, 3+ years software engineering experience in infrastructure or ML systems. Strong proficiency in C++/Python/Go/Rust. Experience with Kubernetes, containerization, and large-scale ML/MLOps infrastructure. Preferred: experience with ML systems engineering, open source inference engines (vLLM, Sglang, TRT-LLM), CUDA/ROCm, GPU profiling, and open-source contributions.