Platform Engineer

About

WriftAI is building the infrastructure layer that makes AI easy to deploy and scale in production. We help teams ship AI-powered products faster by removing the operational complexity behind running models at scale — enabling customers to focus on building, not infrastructure. Our platform provides simple APIs and SDKs that handle model deployment, scaling, and performance optimization behind the scenes, making production-grade AI accessible to engineering teams of all sizes.

The Role

We’re looking for a Platform Engineer to help power the backbone of WriftAI’s infrastructure — the systems that bootstrap projects, manage compute, handle autoscaling, orchestrate workloads, and keep everything running smoothly for developers relying on our platform.

As a Platform Engineer, you will work on critical infrastructure components that enable reliability, scalability, and performance across the WriftAI platform, ensuring we can support everything from early adopters to large-scale enterprise users.

What You'll Do

• Design, build, and operate foundational platform components for provisioning, scaling, and managing compute resources.
• Implement systems for autoscaling, load balancing, and fault tolerance in production.
• Improve and maintain infrastructure for deployment pipelines, orchestration, and monitoring.
• Collaborate with Engineering, DevOps, and SRE to ensure reliability, performance, and observability.
• Participate in architecture decisions that impact core platform capabilities.
• Debug distributed systems and provide long-term fixes for reliability and performance issues.

Minimum Requirements

• Strong software engineering experience (3+ years) with backend or distributed systems.
• Experience building and operating systems on at least one major cloud platform (e.g., AWS, GCP, or Azure).
• Familiarity with workload scheduling, infrastructure automation, or similar platform technologies.
• Solid experience in at least one language commonly used for backend or platform development (e.g., Go, Rust, Python, or similar).
• Understanding of networking, observability, and performance optimization.
• Comfortable working independently and collaboratively in a fast-paced startup environment.

Nice to have

• Experience working on AI or high-performance compute workloads (e.g., GPU scheduling, model serving, or low-latency inference systems).
• Familiarity with container orchestration, infrastructure automation, or scaling systems (e.g., Kubernetes, Amazon ECS, Terraform, autoscaling platforms, edge or distributed compute systems).
• Familiarity with modern observability tooling (logs, metrics, tracing).