
Senior Inference Engineer, AIConfigurator for Dynamo
Owner-facing IC role to build and evolve AIConfigurator's optimization engine and production-quality Python/Rust APIs, CLIs, SDKs, and workflows. Requires 10+ years of software engineering experience and expertise in GPU computing, model serving, performance modeling, benchmarking, and distributed systems to optimize latency, efficiency, parallelism, and resource utilization across NVIDIA GPU deployments (H100/H200/B200/GB200).









