Stack AV jobs

Site Reliability Engineer (Compute Platform focus) at Stack AV responsible for designing and operating batch compute and workflow orchestration systems on Kubernetes. Requires Kubernetes, cloud infrastructure, automation, and Linux expertise; on-call rotation expected. Remote option available (Pittsburgh, PA or remote), salary not disclosed.

Senior Site Reliability Engineer at Stack AV, an autonomous systems company, responsible for ensuring production systems meet service-level objectives through observability, automation, and incident management. Requires Kubernetes, cloud (AWS/GCP), IaC, and Linux expertise; on-call rotation expected. Remote option available (Pittsburgh, PA or remote), but no salary disclosed.

Staff Software Engineer at Stack AV designing architecture for multi-tenant ML inference platforms serving autonomous trucking. Responsibilities include platform architecture across serving, orchestration, control plane, APIs, and model-engine integration; technical leadership across ML Platform and infrastructure teams; and maintaining engineering excellence standards. Requires 7+ years of distributed systems experience and demonstrated cross-team technical leadership. Remote or Pittsburgh-based.

Senior Software Engineer at Stack AV building high-throughput, low-latency ML inference platforms for autonomous trucking. Responsibilities include owning inference subsystems (model onboarding, serving APIs, metering, observability, performance optimization), building multi-tenant control planes, and optimizing GPU performance. Requires strong experience with distributed systems, inference engines (TensorRT, vLLM), and deep learning frameworks (PyTorch). Remote or Pittsburgh-based.