K

Kandou AI

Provides chip-to-chip AI connectivity solutions

Characterization Lead

Hardware Validation & TestingConfirmed live in the last 24 hours
Full-timeSaint-Sulpice, SwitzerlandNo salary listed

About the Job

Requirements

  • 10 to 14 years of experience in SerDes/silicon characterization and/or high-speed channel and signal integrity characterization following degree completion.
  • Direct ownership of a characterization program whose results became datasheet limits or qualification thresholds for a shipping product.
  • Strong VNA measurement experience to 50 GHz or beyond, including de-embedding, mixed-mode S-parameters (Sdd/Scc/Scd/Sdc), and insertion/return-loss mask interpretation.
  • Hands-on TX/RX SerDes characterization, jitter decomposition, BER bathtubs, PVT shmoos, and equalization/adaptation analysis.
  • Demonstrated common-mode and mode-conversion measurement depth, with the ability to distinguish channel behavior from fixture and calibration artifacts.
  • Statistical characterization and guard-band derivation across corners, with clear treatment of measurement uncertainty, sample size, and aging.
  • Experience with VNAs, oscilloscopes of at least 50 GHz bandwidth, BERTs, jitter instrumentation, thermal forcing, and ATE characterization load boards.
  • A BS in Electrical Engineering or equivalent.
  • Technical communication and coordination skills to hand off defensible limits to validation and manufacturing teams.

Responsibilities

  • Lead silicon and channel characterization from measurement planning and bench setup through analysis, limit derivation, and documented hand-off to validation.
  • Characterize TX/RX SerDes performance across process, voltage, and temperature, including swing, jitter, sensitivity, equalization, adaptation, CDR lock, BER bathtubs, and shmoos.
  • Own channel measurements to at least 50 GHz, including de-embedding, insertion/return loss, mixed-mode S-parameters, and common-mode and mode-conversion behavior.
  • Establish reference-paddle baselines and channel classes by gauge, reach, and frequency; correlate HTDR-derived metrics with calibrated VNA measurements.
  • Derive datasheet limits and guard-bands from measured distributions, accounting for uncertainty, sample coverage, and aging; maintain traceable datasets and limit revisions.
  • Assess carrier-loading and forwarded-clock tradeoffs using measured channel data and simulation, and translate the findings into supported configurations and characterization limits.
  • Characterize power, energy per bit, and thermal behavior across operating modes and corners; investigate equalizer noise amplification and channel/thermal interactions.
  • Coordinate shared laboratory equipment and characterization milestones with validation teams; lead technical reviews and deliver limits in time for downstream qualification and screening.

Desired Qualifications

  • Characterization leadership for shipping 100G/lane or 200G/lane retimers, PHYs, AECs, or AOCs.
  • Deep mixed-mode characterization where common-mode behavior affects information transport and link margin.
  • Experience producing datasheet limits that a separate validation team independently qualified.
  • Multi-carrier or proprietary coding schemes, including OFDM-style subcarriers and space-time coding, and their characterization implications.
  • Published work or patents in channel modeling, de-embedding, or SerDes characterization.
  • An MS or PhD with a concentration in communications, RF/microwave engineering, or signal integrity.

About the Company

Kandou AI

Provides chip-to-chip AI connectivity solutions

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.

Company size
201-500
Company stage
Late Stage VC
Total funding
$504.7M
Headquarters
Lausanne, Switzerland
Founded
2011

Recently Posted Jobs

Explore more opportunities at Kandou AI

See more jobs