Senior Staff Inference Performance Engineer

About the role

Join d-Matrix and help build the future of AI inference. We’ve pioneered a memory-centric architecture that brings compute directly into memory, making AI faster, more energy efficient, and accessible on a global scale. From chips and software to rack-scale systems, our team is tackling some of AI infrastructure’s hardest challenges — and shipping breakthrough technology today. If you want to create what comes next and help make infinite inference possible, we’d love to hear from you.

Our culture is built on respect, collaboration, and direct communication. We value humility, we believe our different perspectives lead to better solutions, and we’re looking for people who are driven by execution and energized by hard problems.

Senior Staff Performance Engineer, Inference Cloud

Location: Santa Clara, CA / Remote, US

Role Overview

The Inference Cloud Engineering team builds the deployment and orchestration technology behind d-Matrix’s inference services: an internal cloud where teams test and tune models, and a customer-facing Cloud with self-service inference endpoints and compute. As the team’s Inference Performance Engineer, you will own end-to-end performance of the workloads we deploy, from the moment a request arrives to the moment a result is returned. The standard is that a workload on our orchestrated platform should perform at least as well as it does on bare metal. Today’s workloads include speculative decoding and attention-FFN disaggregation across d-Matrix Corsair accelerators and GPUs, with more heterogeneous architectures coming. Because there is no fixed system to master, the job is a method: profile first, form a hypothesis, test it, and then change the system. You will own the outcome, not every fix. Many root causes sit with other teams, so you will fix what you understand well and hand off the rest with evidence the owning team can act on.

What You Will Do

- Diagnose performance problems across the full serving path, from orchestration (scheduling, placement, networking, autoscaling) to inference internals (batching, KV-cache, prefill/decode, serving framework, driver and runtime, interconnect, host OS and NUMA, accelerator).

- Isolate each problem to a specific layer and owner, then decide whether to fix it directly, route it to the owning team, or both, with a workaround now and a tracked handoff for the permanent fix.

- Write minimal, reproducible problem statements for cross-stack findings so owning teams can act without repeating the investigation.

- Protect throughput, latency, and stability targets for orchestrated workloads by finding and closing gaps against bare metal, such as placement overhead, non-performance power defaults, and extra network hops.

- Assess what it takes to scale from single deployments to fleet operation, including routing, placement, and shared-resource contention.

- Capture each workload’s node requirements (CPU placement, memory and NUMA locality, network path) in the orchestration layer’s configuration so performant deployment is the default.