Fullstack Software Engineer – AI Infrastructure

About the role

Sciforium is building the core serving platform for next‑generation multimodal AI models. The Fullstack Software Engineer will work across C++, Python, and Typescript to create low‑latency, real‑time APIs and user interfaces that power AI applications.

Key responsibilities

• Design and implement a low‑latency chat interface for testing large language models.
• Build the developer console for API key generation, budgeting, and real‑time usage visualisation.
• Integrate Stripe (or similar) to support complex subscription and billing models.
• Develop a dynamic documentation portal that renders API specifications.
• Write CLI/SDK wrappers to simplify client‑side connections to Sciforium’s endpoints.
• Create secure backend API gateways and streaming solutions using FastAPI and low‑latency protocols.

Required profile

• Bachelor’s degree in Computer Science, Engineering or equivalent practical experience.
• 3+ years of software engineering experience with a focus on front‑end development.
• Strong proficiency in Typescript and Python.
• Understanding of responsive design and UX fundamentals.
• Excellent collaboration and communication skills across engineering and ML teams.
• Willingness to work onsite in San Francisco in a fast‑moving, high‑ownership environment.

Required skills

• C++
• Python
• Typescript
• FastAPI
• WebSockets and Server‑Sent Events
• Stripe integration
• Experience with inference engines such as vLLM, Sglang or TRT‑LLM (nice‑to‑have)

What we offer

• Medical, dental, and vision insurance
• 401(k) plan
• Daily lunch, snacks, and beverages
• Flexible time off
• Competitive salary and equity
• Equal opportunity employment