Principal Systems Engineer, Signal-Path Performance & Modeling

Neurophos, Austin, Texas

The role

We are seeking a highly skilled Systems Engineer to own the quantitative, end-to-end performance model of our optical vector-matrix multiplication (OVMM) engine. This role is the technical center of Systems Engineering's performance-modeling focus area: you will lead the end-to-end modeling, analysis, and architectural definition of high-speed communication and signal-processing systems. In this role, you will build and maintain the link and power budgets; quantify impairments and non-idealities across the optical, analog, and digital domains; develop mathematical and behavioral models; define the hardware and algorithmic techniques required to meet aggressive system-level performance targets; and determine how accuracy, throughput, and power trade against one another as the architecture evolves.

Posted pay

$245K–$285K

a year

Compared with similar jobs

This base pay is above the median for principal infrastructure, platform and SRE jobs in other US places.

Median: $220K a year
Other jobs in the group: 121

We compare the middle of each posted range. This is base pay as posted. The group does not include this job.

Location

Austin, Texas

Work type

Onsite

Level

Principal

Experience

7+ years

Skills in the job text

Posted

27 days ago

Last check

9 h ago

Job type

Infra, platform & SRE, Inference & ML systems

The role

What you will do

Primary Responsibilities

Signal-Path Architecture Ownership: Own and define the architecture of the high-speed communication and signal-processing system that converts the digital data stream into an optical signal and back—spanning digital signal processing, D/A and A/D conversion, and the analog/optical signal conditioning surrounding them on both the transmit and receive sides. Define the blocks and processing stages that comprise this system and specify the requirements for each. Negotiate block-level requirements with the photonic and mixed-signal implementation teams who build to this architecture.
Link & Power Budget Ownership: Own and maintain the end-to-end optical and electrical link/power budget for this signal path, keeping it synchronized with the as-designed and as-measured hardware as the architecture evolves.
Signal-Path Modeling: Build and maintain the reference behavioral model of the full TX–channel–RX signal path, capturing optical, analog, quantization, and algorithmic effects with the fidelity needed for architecture decisions and requirements allocation.
Accuracy & Performance Allocation: Allocate NMSE/SNR/SNDR targets across optics, analog, quantization, and algorithmic domains, and update those allocations as component and architecture choices change.
Impairment Analysis: Characterize and model optical, analog, and digital impairments—noise, distortion, jitter, quantization effects, crosstalk, mismatch, and nonlinearity—and quantify their impact on system-level accuracy.
Throughput & Efficiency Trade Studies: Analyze the impact of TX/RX channel configurations and architectural options on TOPS, TOPS/W, and latency. Balance the complexity, risk, and time-to-market of proposed architectural solutions.
Monte Carlo & Time-Domain Simulation: Develop and run statistical (Monte Carlo, corner) and time-domain simulations to quantify design margin and manufacturing robustness.
Model-to-Measurement Correlation: Correlate model predictions with laboratory and silicon measurements; when measured performance does not match simulation, isolate the source of the discrepancy and refine the architecture, model, and allocations accordingly.

Secondary Responsibilities

Represent this system's architecture in roadmap and planning discussions.
Supply quantitative performance data, both predicted and measured, to support other efforts across Neurophos (e.g., customer-facing technical discussions).
Support calibration accuracy-budget definition with sensitivity analysis.
Collaborate with analog, photonic, digital, and software engineers to keep subsystem designs consistent with the architecture and its performance targets.
Mentor engineers in system modeling, communication theory, and architecture/trade-study methodology.
Contribute to intellectual property creation, including invention disclosures and patents.

Principal Systems Engineer, Signal-Path Performance & Modeling

The role

Principal Systems Engineer, Signal-Path Performance & Modeling

The role

What you will do

Primary Responsibilities

Secondary Responsibilities

What you need

Nice to have

Pay and benefits

What we offer

Benefits

About Neurophos

Similar jobs at other companies

Principal Systems Engineer

Optical Engineer - Memphis

Systems Engineer - Compute

AI Systems Performance Architect

System Optic PHY Engineer

Silicon Photonics Systems Test Engineer – Optical Circuit Switches (OCS)

Interview questions

Company facts

Neurophos

Compared with similar jobs