Software Engineer, Inference AI/ML

Join the Inference team to ship production features that improve latency, reliability, and cost for model serving on our GPU platform. As an IC1, you will implement well-scoped changes, learn operational practices, and grow quickly with mentorship. Responsibilities include implementing features in Python/Go/C++ for model-serving services like Triton, vLLM, TensorRT-LLM, and Ray Serve; writing tests and design docs; adding metrics and dashboards; following on-call runbooks; and contributing to b,

BS/MS in CS, EE, or related field, or equivalent practical experience. Foundations in data structures, algorithms, and networked services. Experience with Python or Go (C++ a plus) and Linux fundamentals; Git/CI basics. Exposure to containers and Kubernetes. Curiosity about GPU inference concepts. Preferred: internship or project deploying a microservice or ML inference demo; coursework with PyTorch or TensorFlow; familiarity with Grafana/Prometheus/OpenTelemetry.