General Intuition is hiring a fullstack data platform engineer in New York City to own GPU clusters, data pipelines, storage/IO, and model-serving infrastructure. The role focuses on optimizing scheduling, inference latency, cloud infrastructure, multi-region deployment, and reliability using Kubernetes, Terraform, Python, Go, Rust, and C++.
You will own infrastructure across data pipelines, GPU clusters, storage and I/O, and model-serving runtime. You will optimize scheduling, throughput, inference latency, cloud infrastructure, infrastructure as code, multi-region deployment, and reliability while making technical design decisions for substantial production systems.
Responsibilities
Own orchestration and GPU clusters
Build preprocessing pipelines for raw gameplay video
Optimize disk and network I/O
Optimize production inference through batching, quantization, KV cache, and serving runtimes
Own infrastructure as code, multi-region deployment, and reliability
Make and carry technical design decisions to production