​​​​​​​Model Serving Engineer

Model Serving Engineer to design, build, and operate high-performance, highly reliable inference platforms for serving large machine learning models in production. Focus areas include request routing, batching, caching, autoscaling, GPU utilization, and end-to-end observability across diverse model workloads (LLMs, vision models, and recommendations). Responsibilities include multi-tenant routing, rate limiting, QoS policies, canary releases and automated rollback, incident response for high-availability AI services, security controls at the serving layer, and collaboration with ML and product teams to support model releases. Required skills include distributed systems expertise, proficiency in Python and a systems language (Go, Rust, or C++), experience with LLM inference frameworks (vLLM, TensorRT-LLM), GPU architecture knowledge, Kubernetes and cloud platforms, observability tooling, and performance/cost trade-off optimization.