Director, AI Systems Solutions Engineering - Sunnyvale, CA, United States

Originally posted 29 September 2026 by the employer.

Tensordyne is building a new class of AI inference system designed for high-performance, power-efficient deployment of the world’s most demanding generative AI workloads.

About the role

This role involves leading the technical customer organization that sits between engineering teams and companies deploying the Tensordyne platform for AI inference systems. This involves strategic technical customer engagements from architecture discussions through deployment and expansion.

What you'll do

• Own the technical relationship with key customers and partners from architecture discussions through benchmarking, evaluation, integration, deployment, and expansion.
• Define how Tensordyne demonstrates system performance across KPIs like throughput, tokens/sec/user, ttft, memory utilization, power efficiency, and system density.
• Work with customers and model developers to understand current and emerging HW and model architectures, serving requirements, context lengths, parallelism strategies, and quantization approaches.
• Maintain a technically rigorous understanding of Tensordyne performance relative to GPU and AI accelerator platforms for credible, reproducible comparisons.
• Partner with compiler, runtime, kernel, systems, and SDK teams to enable customer models and workloads on the Tensordyne platform and identify performance improvements.
• Lead technical PoCs, remote evaluations, on-premises beta deployments, integration programs, and production readiness efforts with strategic customers.
• Translate recurring customer requirements into clear priorities for the SDK, compiler, runtime, inference server, model support, orchestration, networking, observability, and system architecture teams.
• Recruit, develop, and lead a small team of Sales/Solutions Engineers capable of managing sophisticated technical engagements.

What you'll need

• Deep understanding of modern AI inference systems, including LLM and multimodal architectures.
• Strong knowledge of AI accelerator and system architecture, including compute, memory hierarchy, interconnect, parallelism, and distributed inference.
• Experience reasoning about inference performance across latency, throughput, memory bandwidth, utilization, batching, context length, prefill, decode, and system scaling.
• Hands-on familiarity with modern AI frameworks and serving environments such as PyTorch, vLLM, SGLang, or Triton.
• Experience working across the boundary between AI software and accelerator hardware, including GPUs or custom silicon.
• Experience benchmarking and optimizing workloads on large-scale AI infrastructure.
• Strong understanding of production inference techniques including quantization, tensor/model/expert parallelism, disaggregated serving, KV-cache management, and distributed execution.
• Demonstrated ability to engage technically sophisticated external organizations, including Sr technical leaders at hyperscalers, cloud providers, model developers, AI infrastructure companies, or large enterprise engineering teams.
• Experience leading Solutions Engineering, Field Engineering, Forward Deployed Engineering, or comparable technical customer teams.

Skills: technical customer engagements, AI infrastructure, benchmarking, model enablement, PoCs