Teams at WEKA

Own the AMG product roadmap for NeuralMesh: define KV-cache/prefix-cache offload, memory tiering, and integrations with inference engines and orchestration. Translate GPU/memory/network tradeoffs into product requirements, validate benchmarks with enterprise customers and GPU-cloud partners, partner with NVIDIA for certifications, and support sales with technical positioning to reduce cost-per-token and improve inference SLAs at scale.

Lead and own end-to-end LLM inference infrastructure, direct a small engineering squad, design and deliver high-throughput low-latency serving systems, remain hands-on (Python/C++/CUDA), solve inference-scale problems (KV caching, RDMA, NVMe, multi-tier GPU memory), and mentor engineers.

Lead alliance strategy across enterprise AI infrastructure, manage partnerships, define solution architectures, and drive GTM enablement while representing the company in industry events.