Software Engineer, Infrastructure
Scaled Cognition8 months ago
Boston, MA, USA +2 moreSenior
Responsibilities
- Design and improve inference infrastructure for AI models.
- Benchmark, profile, monitor, and analyze latency and throughput to drive improvements throughout the stack.
- Collaborate with research scientists and product engineers to streamline the process from model development to production deployment.
Requirements
- Experience deploying systems on major cloud platforms, including AWS, GCP, or Azure.
- Prior experience designing and implementing GPU infrastructure or tooling.
- Strong understanding of scalability and developing secure, highly reliable environments.
- Ability to navigate significant product and technical ambiguity and deliver high-quality solutions.
- Ability to adapt to changing priorities and explore new tools and technologies.
Tech Stack
Categories
About Scaled Cognition
We built Super-Reliable Intelligence to give your customers the right answers every time. Every response is verified against your policies and brand standards, so your customers get the right answer — not a best guess. Deploy the only frontier model for customer service to build and run AI agents at scale. Hallucination-free AI that you and your customers can actually trust.