Director, AI Systems Solutions Engineering

Description

The company is building an AI inference system for fast, power-efficient running of demanding generative AI workloads.

The platform combines its own chips, new AI math, scale-up networking and memory design into one integrated system built for large-scale inference.

Customers include hyperscalers, neoclouds, frontier model developers, enterprises and infrastructure partners.

The company is moving from system development into silicon bring-up, customer validation, beta deployments and production rollout, and is setting up a technical customer group between its engineering teams and those customers.

The company wants a strong technical leader to build and run that group.

Team values: put people first, act with ethics and integrity, think big, aim for excellence, take ownership and get results, make each other better, and value differences.

Responsibilities

• Own and expand the company's most important technical customer accounts.
• Build and manage a small team of Sales and Solutions Engineers covering benchmarking, technical evaluation, NPI, model enablement, AI data center architecture and production deployment.
• Own the technical relationship with key customers and partners from first architecture talks through benchmarking, evaluation, integration, deployment and expansion.
• Define how the company shows system performance on metrics such as throughput, tokens per second per user, time to first token, memory utilization, power efficiency, system density, model accuracy and quality, and other relevant inference measures.
• Work with customers and model developers on current and upcoming hardware and model designs, including serving needs, context lengths, parallelism, model topology, quantization and inference tuning.
• Keep a rigorous view of the company's performance against leading GPU and AI accelerator platforms, making sure customer comparisons are credible, reproducible, current and tied to real deployment needs.
• Work with compiler, runtime, kernel, systems and SDK teams to bring key customer models and workloads onto the platform and find performance gains.
• Lead technical proofs of concept, remote evaluations, on-premises beta deployments, integration programs and production readiness work with strategic customers.
• Turn recurring customer needs into clear priorities for the SDK, compiler, runtime, inference server, model support, orchestration, networking, observability and system architecture teams.
• Stay current on model architectures, inference methods, accelerator roadmaps, serving frameworks, competing systems, benchmarking methods and market shifts.
• Turn early engagements into repeatable benchmarks, evaluation frameworks, reference architectures, deployment playbooks, documentation, demos and technical materials for a growing customer base.
• Work directly with frontier model builders, hyperscalers, neoclouds, developers, infrastructure partners and strategic customers as they evaluate and deploy the systems.
• This is not a traditional pre-sales role. You will move between a customer architecture review, shaping product capabilities and roadmaps, and leading a technical evaluation with hyperscalers and frontier AI companies, as models and requirements change constantly.

Requirements

• Proven AI systems leadership with deep technical skill and sound judgment.
• Deep understanding of modern AI inference systems, including LLM and multimodal architectures.
• Strong knowledge of accelerator and system architecture: compute, memory hierarchy, interconnect, parallelism and distributed inference.
• Ability to reason about inference performance across latency, throughput, memory bandwidth, utilization, batching, context length, prefill, decode and system scaling.
• Hands-on experience with AI frameworks and serving environments such as PyTorch, vLLM, SGLang, Triton or comparable systems.
• Experience across the line between AI software and hardware, ideally with GPUs, custom silicon or emerging AI accelerators.
• Experience benchmarking and tuning workloads on large-scale AI infrastructure.
• Solid grasp of production inference methods: quantization, tensor, model and expert parallelism, disaggregated serving, KV-cache management, distributed execution and related optimizations.
• Proven ability to engage sophisticated external technical teams, such as senior engineers at hyperscalers, cloud providers, model developers, AI infrastructure companies or large enterprises.
• Experience leading strong Solutions Engineering, Field Engineering, Forward Deployed Engineering or similar technical customer teams.
• Comfort working in a fast-moving setting where product, software stack, competition and customer needs change at the same time.
• Particularly relevant: experience at organizations building or deploying GPU or custom AI accelerator platforms, large-scale AI inference infrastructure, frontier or foundation models, hyperscale cloud infrastructure, AI serving and orchestration platforms, compiler, runtime or distributed AI systems, or high-performance computing and distributed systems.
• Especially valuable: experience taking a new accelerator architecture or AI infrastructure platform from early access through customer validation to production.