Staff Systems Engineer, Signal-Path Performance & Modeling

Job Title

Staff Systems Engineer, Signal-Path Performance & Modeling

Role Summary

Lead the quantitative, end-to-end performance and power modeling for an optical vector-matrix multiplication (OVMM) engine. You will build and maintain link and power budgets, develop behavioral signal-path models, run system-level simulations, and translate results into actionable allocations for architecture and hardware teams.

This is a full-time onsite role based in Austin, TX or Sunnyvale, CA reporting to the Chief Systems Engineer.

Experience Level

Senior - typically requires 5+ years of relevant professional experience in communication systems architecture, link-budget/signal-chain modeling, or performance modeling of optical or high-speed electrical communication systems.

Responsibilities

Primary responsibilities focus on modeling, simulation, and allocation of performance and power across the optical and electrical signal path.

• Own and maintain the end-to-end optical and electrical link/power budget for the OVMM signal path and keep it synchronized with design and measurements.
• Build and maintain a reference behavioral model of the TX–channel–RX path that captures optical, analog, quantization, and algorithmic effects.
• Allocate NMSE/SNR/SNDR targets across optics, analog, quantization, and algorithmic domains and update allocations as designs evolve.
• Characterize and model impairments (noise, distortion, jitter, quantization, crosstalk, mismatch, nonlinearity) and quantify their impact on system accuracy.
• Run statistical (Monte Carlo, corner) and time-domain simulations to quantify margin and manufacturing robustness.
• Correlate model predictions with laboratory and silicon measurements; isolate and resolve discrepancies between measurement and simulation.
• Provide quantitative performance data for architecture and requirements trade studies; support calibration accuracy budgets and sensitivity analyses.
• Collaborate with analog, photonic, digital, and software engineers to align subsystem designs with system-level targets and mentor engineers in modeling and trade-study methods.

Requirements

Must-have technical skills and experience required to perform the role; preferred skills listed separately.

• Must-have: 5+ years of professional experience in communication systems architecture, link-budget/signal-chain modeling, or performance modeling of optical or high-speed electrical communication systems.
• Must-have: Deep knowledge of modulation formats, equalization, synchronization and estimation, quantization effects, and coding-gain concepts and how they feed into end-to-end performance budgets.
• Must-have: Expert-level proficiency in Python (NumPy/SciPy) and/or MATLAB/Simulink for behavioral modeling, Monte Carlo simulation, and statistical/time-domain analysis.
• Must-have: Demonstrated ownership of an end-to-end optical or RF link or SNR/noise budget and ability to update allocations and predict system-level impact.
• Must-have: Strong written and verbal communication skills for cross-functional collaboration and presenting quantitative trade-offs to technical leadership.
• Nice-to-have: Experience with optical communication links (coherent or direct-detection) or high-speed SerDes/networking standards (Ethernet, PCIe, OIF-CEI).
• Nice-to-have: System-level modeling experience for high-speed ADC/DACs, sampling, quantization, and synchronization across multiple devices.
• Nice-to-have: Familiarity with Cadence Virtuoso/Spectre to validate behavioral models against circuit-level simulation and hands-on lab or silicon bring-up experience.
• Nice-to-have: Familiarity with photonic integrated circuits, silicon photonics, or optical transceiver systems.

Education Requirements

MS or PhD in Electrical Engineering, Applied Physics, or a closely related field with emphasis on communication theory, signal processing, or mixed-signal systems.

About the Company

Company: Neurophos

Headquarters: Sunnyvale, California, United States

Startup developing silicon-photonic AI accelerator chips that use programmable metasurfaces and dense optical cells to perform matrix multiplications at the speed of light, targeting large-scale AI inference with much higher energy efficiency and performance than traditional electronic approaches.