N

Neurophos

Optical metasurface AI accelerators

Staff Silicon Photonics Engineer - Receiver, Rx

Silicon & ASIC DesignConfirmed live in the last 24 hours
Full-time

About the Job

Requirements

  • A PhD in a relevant field, such as Electrical Engineering, Applied Physics, or Physics.
  • Three years of relevant experience in high-speed silicon photonics, focused on photodetectors and receiver PICs.
  • Hands-on design experience with Ge-on-Si or equivalent high-speed photodetectors, including trade-offs among responsivity, bandwidth, capacitance, and dark current.
  • Proficiency with photonic and device simulation tools such as Lumerical/Ansys, COMSOL, Synopsys TCAD, or equivalent, and circuit-level modeling of photodetectors.
  • Experience laying out and taping out designs in a silicon photonics foundry PDK, such as KLayout, gdsfactory, Cadence Virtuoso, or equivalent.
  • Working knowledge of optical receiver fundamentals, including TIA interfacing, noise, sensitivity, and PAM4 signal integrity.

Responsibilities

  • Define the Rx PIC architecture, including optical input coupling using free-space and waveguide approaches, routing, demultiplexing where needed, and layout of dense photodetector arrays, against system-level link and power budgets.
  • Design and optimize high-speed photodetectors, including Ge-on-Si PIN and avalanche detectors, waveguide-coupled and surface-normal, for responsivity, dark current, capacitance, bandwidth, linearity, and saturation.
  • Model the device and receiver with optical, electrical, and RF simulation, including Lumerical FDTD/CHARGE/INTERCONNECT, HFSS, and TCAD, and develop photodetector equivalent circuits for co-design with the TIA.
  • Work with the electronic IC team on the PD–TIA interface, including pad and interconnect parasitics, bias, input-referred noise, and sensitivity, and support flip-chip, 3D, and co-packaged integration.
  • Analyze array-level optical and electrical crosstalk, uniformity, thermal behavior, and yield, and define test structures and design-for-test features to measure them.
  • Lead layout, verification, and tapeout of Rx PIC test vehicles and product blocks in foundry silicon photonics PDKs.
  • Support die- and wafer-level characterization with the test team, measuring responsivity, dark current, O/E bandwidth, sensitivity, and BER, and use measurements to calibrate models and improve the next design.
  • Evaluate new detector materials, structures, and coupling approaches that could improve receiver performance or density beyond current platform capabilities.

Desired Qualifications

  • Five or more years of experience developing high-speed silicon photonics receivers or photodetectors.
  • Experience taking devices through the full design-to-tapeout-to-fabrication-to-test cycle.
  • Experience designing large or dense photodetector arrays, or free-space and surface-normal optical coupling to photonic chips.
  • Experience co-designing photodetectors with CMOS/SiGe TIAs in monolithic, flip-chip, or 3D-integrated receivers.
  • Experience with advanced detector platforms, such as avalanche photodiodes and III-V/Si heterogeneous detectors, or a track record of publications or patents in photodetectors and receivers.

About the Company

Neurophos

Optical metasurface AI accelerators

Neurophos designs AI accelerator chips built with optical metasurfaces and silicon photonics to deliver high-density, energy-efficient AI computation for data centers. Its processors are designed to shrink optical components by about 8000x, increasing compute power per dollar spent and reducing both capital and operating expenditures. The product works by using optical processing techniques that handle AI inference workloads more efficiently than traditional GPUs or electronic AI accelerators, enabling faster throughput with lower power use. Neurophos differentiates itself by combining optical metasurfaces with silicon photonics to achieve higher density and energy efficiency, targeting data centers and enterprises that need scalable, cost-sensitive AI inference. The company aims to reshape the AI landscape by offering faster, denser, and more energy-efficient AI computation while lowering the total cost of ownership for data centers.

Company size
51-200
Company stage
Series A
Total funding
$117.2M
Headquarters
Austin, TX
Founded
2020

Recently Posted Jobs

Explore more opportunities at Neurophos

See more jobs