Scaled Cognition
Software Engineer, Infrastructure
New York · On-site · Full-time · Posted Jan 29, 2026
About the job
Designs and improves inference infrastructure for AI models, optimizing performance and supporting production deployment.
What you'll do
- Design and improve AI model inference infrastructure.
- Benchmark, profile, monitor, and analyze latency and throughput, then improve performance across the stack.
- Work with research scientists and product engineers to streamline model development through production deployment.
What they ask for
- Experience deploying systems on major cloud platforms (AWS, GCP, Azure).
- Prior experience designing and implementing GPU infrastructure / tooling.
- Strong sense for scalability and developing secure, highly reliable environments.
Tools
AWS, GCP, Azure
AI focus
Build and optimize inference infrastructure that powers AI models and supports their deployment to production.
Model-written summary · the original posting is authoritative