System & Fpga Platform Engineer

About Symatics
Symatics is a Singapore-headquartered fabless semiconductor startup building the MPU, a deterministic AI inference accelerator for large language models. Instead of scheduling work at runtime, the MPU executes a compiler-generated static schedule across a large on-die compute array and a low-latency multi-chip fabric, on a 5nm-class node with commodity GDDR memory. The target is predictable, low-latency inference for MoE and agentic workloads at rack scale.

The founding team comes from ATI/AMD, Lightelligence, eTopus and the wider GPU, Ser Des and AI-silicon community. Toronto is our MPU design centre;
Hsinchu is the centre for the fabric switch.

What you will do
Own the path from architecture to a working system: FPGA proof-of-concept today, board/host/rack-level definition for silicon next.

Build and maintain the multi-FPGA prototype (AMD Versal / Alveo class, HBM and PAM4 transceivers) — Toronto will host one of two lab rigs
Port and partition RTL to FPGA; timing closure, transceiver bring-up, host PCIe link, debug infrastructure
Define system-level requirements: host interface, board, power, thermal, clocking/synchronisation across many accelerators
Write bring-up plans and lab validation procedures for first silicon
Work with software on drivers, firmware and demo workloads

What we are looking for
BS/MS EE/CE; 7+ years in FPGA prototyping, system/board design or silicon bring-up
Strong Vivado / Versal flow; multi-gigabit transceivers; PCIe endpoint design
Lab skills: scopes, BERT, protocol analysers; methodical debug
Scripting (Python/Tcl) and basic Linux driver-level literacy

Nice to have
Rack-scale or multi-accelerator system design (GPU servers, switch systems)
SI/PI awareness for 32G NRZ / 64G PAM4 links
Post-silicon validation of GPU, NPU or networking ASICs

Pay: $-$ per year

Work Location:

In person