SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Sciforium is an AI infrastructure company building next-generation multimodal AI models and a proprietary high-efficiency serving platform. Backed by multi-million-dollar funding and direct sponsorship from AMD, the company is scaling rapidly to develop the full stack powering frontier AI models and real-time applications.
In this role, you'll work on core systems that power Sciforium's multimodal AI models, helping build the model serving platform across C++, Python, runtime execution, and distributed infrastructure. You'll create a fast, reliable engine for real-time AI applications while gaining hands-on experience with performance engineering, large-scale AI model optimization and deployment, and collaborating closely with ML researchers and experienced systems engineers.
Key responsibilities include:
- Designing and building a low-latency chat interface for users to test LLMs
- Creating a developer console where users generate API keys, set budget limits, and view real-time usage graphs
- Integrating Stripe or similar payment processors to handle complex subscription models
- Building a dynamic API reference documentation portal
- Writing CLI/SDK client-side wrappers to help users connect to API endpoints
- Developing secure API gateways and implementing low-latency streaming solutions
You should have a Bachelor's degree in Computer Science, Engineering, or related field (or equivalent practical experience), 3+ years of software engineering experience with a focus on frontend development, and strong proficiency in TypeScript and Python. Understanding of responsive design, UX fundamentals, and ability to collaborate across engineering and ML teams is essential. The role requires working from the office in a fast-moving, high-ownership team culture.
Nice-to-have skills include experience with ML systems engineering, open-source inference engines (vLLM, Sglang, TRT-LLM), streaming expertise (WebSockets, Server-Sent Events), Stripe billing integration, API documentation best practices, and familiarity with FastAPI or vLLM backends.
