3–5 years of product management experience, ideally in cloud infrastructure, ML platforms, or developer tools. Strong technical foundation (e.g. Computer Science or Engineering degree) with ability to dive deep into model architectures and serving systems. Familiarity with modern ML inference tools and frameworks (e.g., Triton Inference Server, vLLM, SGLang, TensorRT-LLM, Dynamo, KServe, Ray Serve). Proven track record of delivering technically complex products that support distributed and high-throughput ML pipelines. Strong communicator with experience working across engineering, research, and customer-facing teams.