Software Engineer, Backend

Sciforium•San Francisco, CA

32d•Onsite

About The Position

This role offers a unique opportunity to work on the core systems that power Sciforium’s multimodal AI models. You’ll help build the model serving platform working across C++, Python, runtime execution, and distributed infrastructure to create a fast, reliable engine for real-time AI applications. You’ll gain hands-on experience with performance engineering, learn how large AI models are optimized and deployed at scale, and collaborate closely with ML researchers and experienced systems engineers. If you enjoy low-level programming, care deeply about performance, and want exposure to the full AI stack, this role provides both high-impact work and strong growth potential.

Requirements

Bachelor’s degree in Computer Science, Engineering, or a related technical field (or equivalent practical experience)
3+ years of software engineering experience, with a focus on infrastructure or machine learning systems.
Strong proficiency in C++/Python/Go/Rust
Experience with Kubernetes, Containerization
Experience in building large scale ML/MLOps infrastructure
Strong collaboration and communication skills, with the ability to work effectively across engineering and ML teams.
Comfortable working from the office and contributing to a fast-moving, high-ownership team culture.

Nice To Haves

Experience with ML systems engineering, open source inference engine like vLLM, Sglang, or TRT-LLM
Proficiency in CUDA or ROCm and experience with GPU profiling tools
Contributions to open-source ML or HPC infrastructure

Responsibilities

Build the model serving platform, including API, Control Plane, Billing, Monitoring, and distributed inference features.
Collaborate with ML researchers to integrate new multimodal models into production workflows.
Write reliable, maintainable code with strong testing and documentation practices.
Provide operational support for keeping our production services highly performant, available and reliable
Help troubleshoot complex issues across runtime, service, and GPU layers, working closely with other engineers.