Physical Design Engineer
Kandou AI
Physical Design Engineer
Kandou AI
Provides chip-to-chip AI connectivity solutions
At Kandou, we are redefining the economics of AI infrastructure. Our mission is to democratise AI by significantly reducing the Total Cost of Ownership (TCO) of hardware systems — a critical barrier to scalable adoption.
Our proprietary MIMO-over-copper technology powers a high-performance, chiplet-based AI memory fabric that is both scalable and energy-efficient. Unlike traditional interconnects, our solution reduces power consumption significantly while preserving high bandwidth and ultra-low latency — unlocking unprecedented efficiency for AI training and inference at scale.
Job title: Advanced R&D - Physical Design Engineer
Location : Lausanne, Switzerland
The Physical Design (PD) Engineer translates high-speed communication IP digital designs into physical GDSII layouts for advanced FinFET nodes. You will bridge logic design, owning block-to-chip implementation from netlist to final physical sign-off, ensuring PPA (Power, Performance, and Area) targets are met.
Immediate key objective
Drive block-level physical implementation—covering synthesis, SDC constraints, floorplanning, placement, CTS, and routing—meeting strict frequency, area, and power targets.
Execute timing closure across multiple corners and modes (MCMM) utilizing static timing analysis (STA) and generating targeted ECOs.
Drive full physical verification closure sign-off in deep-submicron FinFET technologies.
Responsibility
Own block synthesis, floorplanning, placement optimization, CTS, and routing.
Develop and refine SDC constraints to ensure design intent matches physical realization.
Collaborate with the digital design team to resolve logic or architectural bottlenecks affecting P&R convergence.
Generate progress reports, document implementation flows, and prepare sign-off packages for tape-out.
Required Experience
5+ years of hands-on physical design experience focusing on synthesis, SDC constraints, CTS, and place and route for high-speed systems.
Strong technical background in deep-submicron CMOS/FinFET physical effects, crosstalk, and high-frequency clock network design.
Proven experience of taking complex blocks from netlist through successful physical implementation.
Direct experience with advanced low-power implementation techniques (UPF, power gating).
Proven tape-out experience in advanced FinFET nodes (e.g., 7nm, 5nm, or 3nm).
Experience handling complex block-to-chip hierarchical assembly, pin placement, and top-level routing constraints..
Required Skills
Expert proficiency with industry-standard implementation and sign-off tools (e.g., Cadence Genus/Innovus/Tempus or Synopsys Design Compiler/ICC2/PrimeTime, and Calibre).
Deep understanding of SDC creation, and MCMM timing management.
Strong scripting skills (Tcl, Python) for flow automation and design data analysis.
Analytical mindset to debug congestion routing issues, and complex timing violations.
Self-motivated with strong sense of ownership; effective communicator and team player
Required Education
Masters or Ph.D. in E.E., Communications or other relevant fields
Kandou AI designs and sells semiconductor connectivity hardware for AI workloads. It provides a memory fabric and CXL controllers that link processors to memory, enabling scalable, energy-efficient AI inference and training clusters built from affordable hardware. Using Copper MIMO interconnect, it reduces energy per bit and supports features like offloading AI training collectives, switchless memory for in-memory databases, and field-repairable co-packaged optics for better cooling. By targeting the data-movement bottleneck between processors and memory and offering chiplet-based fabrics and IP licensing, Kandou AI aims to make scalable AI infrastructure more accessible to hyperscalers, data centers, and system integrators.
Explore more opportunities at Kandou AI