Role Overview
As a Systems Engineer on our Experiments & Integration team, you will be the engineer who answers the urgent questions. Hardware, software, and customer teams bring the simulation team a steady stream of unplanned requests: run this model on the emulator, measure that bottleneck, help this team integrate. You will work across all of those teams, on both simulation and hardware emulation, to turn each request into a fast, measured answer.
The work is varied and hands-on: standing up a new model on the emulator, profiling where time goes, or trying a configuration a stakeholder wants to see. You will own this queue so the engineers building the roadmap can stay focused on it, and you will leave each investigation behind as a reusable model, test, or script.
Key Responsibilities
Rapid Response and Experiments
- Serve as the first responder for simulation and emulation requests from hardware, software, and customer teams, partnering with the existing experiments and integration engineers so urgent asks get answered while roadmap work stays protected.
- Run quick experiments and demos, such as getting a new LLM running on the emulator, profiling where time goes, or trying a configuration a stakeholder wants to see.
Performance Measurement
- Measure and explain performance using counters, traces, and end-to-end timing, reported along with their limits and their drivers.
Integration and Reusable Assets
- Help other teams build on the simulators and the emulation setup when they need integration support.
- Convert each investigation into a reusable asset, such as a calibrated model, a repeatable experiment, or a regression test.
Required Qualifications
- 4+ years of experience as a hands-on systems or performance engineer.
- Demonstrated experience running LLM inference workloads end to end and finding where time goes, including weight loading, memory bandwidth, and host-device synchronization.
- A strong understanding of performance measurement, including counters, execution traces, profiling, and reporting results with their limits.
- Hands-on experience with host-side driver and runtime code, and comfort working close to hardware.
- Ability to move fast on loosely specified requests, make assumptions explicit, and finish by making the result repeatable.
- Strong Rust skills, or expert-level C/C++ skills and a willingness to work in Rust day to day, along with proficiency in Python and fluency with Linux, shell scripting, containers, and CI.
- Excellent communication skills, with the ability to give stakeholders a direct answer, what it rests on, and what to do next.
Preferred Qualifications
- Experience with hardware emulators such as Cadence Palladium or Synopsys ZeBu, or with FPGA boards.