Originally posted September 29, 2026 by the employer.
About the role
This role involves owning and growing technical customer engagements for Tensordyne's AI inference system, which combines purpose-built silicon, AI math, optimized scale-up networking, and memory architecture into a tightly integrated system.
What you'll do
- Own the technical relationship with key customers and partners from initial architecture discussions through deployment and expansion.
- Define how Tensordyne demonstrates system performance across KPIs like throughput, tokens/sec/user, ttft, memory utilization, and power efficiency.
- Work with customers to understand current and emerging hardware and model architectures, serving requirements, and inference optimization.
- Maintain a rigorous understanding of Tensordyne performance relative to GPU and AI accelerator platforms.
- Partner with compiler, runtime, kernel, systems, and SDK teams for model enablement and optimization.
- Lead technical PoCs, remote evaluations, beta deployments, and production readiness efforts with strategic customers.
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, and distributed inference.
- Experience reasoning about inference performance across latency, throughput, memory bandwidth, utilization, batching, and context length.
- 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, and disaggregated serving.
- Demonstrated ability to engage technically sophisticated external organizations including Sr technical leaders at hyperscalers or cloud providers.
- Experience leading high-performing Solutions Engineering, Field Engineering, or Forward Deployed Engineering teams.
Skills: technical customer engagements, AI infrastructure, benchmarking, model enablement, PoCs
More semiconductor jobs: Field applications engineer jobs · Sunnyvale jobs
Tracked in our index since 30 Sept 2026. This is our observation date, not the employer posting date. Specialty: Applications FAE (AI ML Hardware). 130 active roles in this specialty at 24 employers in our index, as of 18 Nov 2026.
How we counted: postings read from employer career sites. How we count