Staff Systems Engineer
Neurophos
Staff Systems Engineer
Neurophos
Optical metasurface AI accelerators
The demand for new data centers and AI compute is rapidly outpacing the planet's energy capacity. Digital solutions are hitting a power wall as we approach the physical limits of traditional silicon. Conquering this bottleneck means rethinking the fundamental architecture of inference compute. The industry's current path can't meet the need, so we're taking a different approach.
Instead of traditional electronic circuits, we use silicon photonics and an active, programmable metasurface to perform matrix multiplications at the speed of light. Our optical cells are 10,000x smaller than traditional photonic components, enabling unprecedented density. By using photonics instead of electricity, our chips become more efficient as they scale. This architecture will deliver up to 100 times the energy efficiency of existing solutions while significantly improving performance for large-scale AI inference.
We’ve assembled a world-class team of industry veterans and recently raised a $110M Series A led by Gates Frontier. Participants include M12 (Microsoft’s Venture Fund), Carbon Direct Capital, Aramco Ventures, Bosch Ventures, Tectonic Ventures, Space Capital, and others.
Join us and shape the future of computing!
Location: Austin, TX. Full-time onsite position.
Reports To: Chief Systems Engineer
FLSA Status: Exempt
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.
You will spend the bulk of your time running system-level simulations, translating them into defensible allocations that the rest of the organization can design against. If you have deep communication-theory and signal-processing intuition, are fluent turning a signal chain into a quantitative model, and want to be the person who can answer "where does the system actually lose its margin," this role will let you define the performance envelope of a first-of-its-kind computing platform.
Primary Responsibilities
Link & Power Budget Ownership: Own and maintain the end-to-end optical and electrical link/power budget for the OVMM 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 trades 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, including 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 channel count, TX/RX configuration, and architectural changes on TOPS, TOPS/W, and latency, and determine whether a proposed architectural change is worth its additional power or complexity.
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 model and allocations accordingly.
Secondary Responsibilities
Supply architecture and requirements trade studies (led by the Architecture & Requirements focus area) with quantitative performance data.
Support calibration accuracy-budget definition (led by the Calibration, Bring-Up & Verification focus area) with sensitivity analysis.
Collaborate with analog, photonic, digital, and software engineers to keep subsystem designs consistent with system-level performance targets.
Mentor engineers in system modeling, communication theory, and quantitative trade-study methodology.
Contribute to intellectual property creation, including invention disclosures and patents.
Degree: MS or PhD in Electrical Engineering, Applied Physics, or a closely related field, with emphasis on communication theory, signal processing, or mixed-signal systems.
Experience: 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.
Communication Theory & Signal Processing: Deep knowledge of modulation formats, equalization, synchronization and estimation, quantization effects, and coding-gain concepts, and how each factors into an end-to-end performance budget.
System Modeling: Expert-level proficiency in Python (NumPy/SciPy) and/or MATLAB/Simulink for behavioral modeling, Monte Carlo simulation, and statistical/time-domain analysis.
Link Budget & Noise Analysis: Demonstrated ownership of an end-to-end optical or RF link budget (or equivalent SNR/noise budget), including the ability to update allocations when a component or architecture choice changes and predict the system-level impact.
Communication: Excellent written and verbal communication for cross-functional collaboration with analog, digital, photonic, and software engineers, and the ability to present quantitative trade-offs clearly to technical leadership.
Experience with optical communication links, coherent or direct-detection architectures, or high-speed SerDes/networking standards (Ethernet, PCIe, OIF-CEI).
System-level modeling of high-speed data converters (ADC/DAC), including quantization, sampling, and multi-device synchronization effects.
Familiarity with Cadence Virtuoso and Spectre sufficient to validate behavioral models against circuit-level simulation.
Hands-on laboratory characterization or silicon/system bring-up experience.
Familiarity with photonic integrated circuits, silicon photonics, or optical transceiver systems.
This is an opportunity to play a pivotal role in an innovative startup redefining the future of AI hardware. Work on game-changing technology at the intersection of photonics and AI as part of a collaborative, brilliant team. You’ll contribute to a platform that redefines computational performance and accelerates the future of artificial intelligence. Come help us bring this transformative technology to the world.
Join a team that invests in your future and your well-being. At Neurophos, we offer:
100% coverage of base health plan premiums for you and your dependents, plus HSA contributions.
Unlimited PTO. No rigid vacation banks, just a focus on delivery.
401(k) matching and stock option opportunities to ensure our success is your success.
Full suite of voluntary benefits, including Dental, Vision, Life, Hospital, Critical Illness, and Accident insurance.
Personalized Benefits. Choose the plans that fit your life and take the cash back for those that don’t.
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.
Explore more opportunities at Neurophos