VP of Software Engineering

Key Responsibilities:

• Foundational Stack Ownership: Architect and deliver the end-to-end software stack required to run high-efficiency AI inference workloads in data centers:
• Hardware Bring-Up & Embedded SW: Drive custom firmware, Linux kernel driver design, memory management optimization, and hardware-software co-design for early-stage ASIC, CPU, and GPU architectures.
• AI Compilation & Inference Runtimes: Build high-performance AI compiler paths and runtime engines (e.g., Triton, TVM, MLIR, OpenXLA) capable of executing complex model topologies with peak hardware utilization.
• Data Center Scale & Orchestration: Design the software abstraction and virtualization layers needed to seamlessly cluster, schedule, and orchestrate our silicon across distributed data center infrastructure (e.g., Kubernetes, Ray, Slurm).
• Early-Stage Team Building: Recruit, mentor, and hands-on manage a highly agile, world-class engineering team spanning embedded systems, compiler design, and infrastructure engineering.
• Hardware-Software Co-Design: Collaborate intensely with silicon architects and hardware engineering teams to evaluate workload bottlenecks, running real-world model benchmarks to directly influence future chip revisions.
• Agile Product Delivery: Establish lean, rapid software development lifecycles. Shift quickly from early proof-of-concept and chip bring-up to alpha/beta releases for early data center customers.
• Customer-Centric Ecosystem Integration: Ensure our software stack exposes clean, frictionless APIs and frameworks so enterprise data center clients can seamlessly swap their workloads onto our hardware.

Requirements:

• Proven Executive Leadership: 10+ years of software engineering experience, with a track record as a VP of Engineering, VP of R&D, or Head of Software leading high-performing, multi-layered engineering organizations.
• Startup DNA: Proven experience navigating the fast-paced, high-ambiguity landscape of early-stage startups or hardware bring-up phases. Comfortable being both a strategic architect and a hands-on technical driver.
• Data Center & Compute Expertise: Deep technical understanding of data center compute workloads, distributed system scalability, and the infrastructure requirements for high-density AI inference deployment.
• Cross-Domain Competency: A career that effectively blends silicon-adjacent development with high-level software infrastructure:
• Solid grounding in low-level environments, kernel-level drivers, memory layout, and semiconductor ecosystem dynamics (such as ARM or custom compute blocks).
• Direct experience building or managing teams that deal with deep learning compilation frameworks, model optimization (quantization, pruning), and high-throughput execution engines.
• Strategic & Pragmatic Execution: Exceptional capability to translate early-stage business milestones into crisp software roadmaps, focusing engineering resources on time-to-market and performance benchmarks rather than over-engineering.