the client is hiring a senior software leader for a founder-level VP role focused on AI inference and high-performance software. In this position, you will influence system architecture, team design, and product direction, with a long-term focus on software acceleration that may extend toward programmable hardware and future silicon. You will partner closely with founders and external stakeholders to guide infrastructure strategy and support production adoption of advanced inference capabilities.
You will lead the architecture and delivery of a high-performance AI inference software stack covering runtime, scheduling, serving, and system optimization. You will build and mentor a small elite engineering team while staying hands-on with code, technical design, and execution. Responsibilities also include improving throughput, latency, utilization, and cost efficiency across modern accelerator-based deployments and distributed environments, as well as establishing engineering standards for hiring, release quality, experimentation, and cross-functional collaboration.
To succeed, you should have deep experience building or optimizing production-scale AI inference or distributed systems software for accelerator-rich environments. You should have strong systems expertise in areas such as GPU programming, kernel optimization, runtime design, communication layers, caching, batching, or scheduling, along with a track record of shipping technically difficult platforms where performance, reliability, and scalability are critical. Preferred experience includes familiarity with modern model serving patterns, speculative execution approaches, and performance measurement for large-scale AI workloads, plus proven leadership of senior engineers and the ability to operate effectively in an early-stage environment with high ambiguity.