About Celestial AI
As Generative AI continues to advance, the performance drivers for data center infrastructure are shifting from systems-on-chip (SOCs) to systems of chips. In the era of Accelerated Computing, data center bottlenecks are no longer limited to compute performance, but rather the system’s interconnect bandwidth, memory bandwidth, and memory capacity. Celestial AI’s Photonic Fabric™ is the next-generation interconnect technology that delivers a tenfold increase in performance and energy efficiency compared to competing solutions.
The Photonic Fabric™ is available to our customers in multiple technology offerings, including optical interface chiplets, optical interposers, and Optical Multi-chip Interconnect Bridges (OMIB). This allows customers to easily incorporate high bandwidth, low power, and low latency optical interfaces into their AI accelerators and GPUs. The technology is fully compatible with both protocol and physical layers, including standard 2.5D packaging processes. This seamless integration enables XPUs to utilize optical interconnects for both compute-to-compute and compute-to-memory fabrics, achieving bandwidths in the tens of terabits per second with nanosecond latencies.
This innovation empowers hyperscalers to enhance the efficiency and cost-effectiveness of AI processing by optimizing the XPUs required for training and inference, while significantly reducing the TCO2 impact. To bolster customer collaborations, Celestial AI is developing a Photonic Fabric ecosystem consisting of tier-1 partnerships that include custom silicon/ASIC design, system integrators, HBM memory, assembly, and packaging suppliers.
ABOUT THE ROLE
Celestial AI is looking for a motivated digital designer with experience in Digital Signal Processing to work on next generation CAI Photonic Fabric. In this role, you will be responsible for designing, implementing, and optimizing signal processing algorithms to solve complex problems in high-speed SERDES. This role is a part of ASIC design group and will be working with Analog Mixed signals (AMS) and architecture teams for algorithm design, modeling, simulations, and system integration for Celestial AI's high-speed link design.
ESSENTIAL DUTIES AND RESPONSIBILITIES
- Design & Development: Develop and implement digital algorithms and systems for High-speed SERDES, focusing on optimizing performance and efficiency.
- Algorithm Optimization: Analyze and optimize DSP algorithms for low-power, high-performance, and real-time processing constraints on embedded platforms or hardware.
- Software Development: Work with software team to provide programming sequences for the digital hardware blocks.
- Simulation & Testing: Conduct simulations and performance testing of DSP algorithms using MATLAB/Simulink and System Verilog.
- Define synthesis constraints for modules and SOC and collaborate with Synthesis and Physical Design teams for implementation.
- Collaboration: Work closely with cross-functional teams, including hardware engineers, software developers, and system architects, to integrate DSP algorithms into larger systems and ensure their proper functionality.
- Documentation: Create detailed documentation for algorithms, design processes, and testing procedures to ensure clarity and reproducibility.
- Research & Innovation: Stay up to date with the latest DSP techniques, tools, and industry trends, and incorporate innovative solutions into Celestial AI's designs.
QUALIFICATIONS
- Education: Bachelor’s with 8+ years of experience, Master’s with 6+ years of experience, or Ph.D. degree with 4+ years of experience.
- Experience:
- Strong experience in DSP algorithm design, implementation, and optimization.
- Expertise in RTL design using SystemVerilog and strong knowledge of formal verification methodologies (SVA, UVM).
- Experience with real-time DSP systems, hardware acceleration (e.g., FPGA), and embedded systems is a plus.
- Experience with tools such as MATLAB, Simulink, or similar DSP software for algorithm development and simulation.
- Skills:
- Proficiency in programming languages: MATLAB/Simulink and SystemVerilog.
- Knowledge of signal processing concepts such as FFT, filtering, modulation/demodulation, noise reduction, and error correction.
- Familiarity with hardware/software co-design, and implementation of DSP algorithms on embedded platforms.
- Problem-Solving: Excellent analytical and troubleshooting skills, with the ability to solve complex signal processing problems in real-time environments.
- Communication: Strong verbal and written communication skills to effectively collaborate with teams and document processes.
LOCATION: Orange County, CA
For California Location:
As an early stage start up, we offer an extremely attractive total compensation package inclusive of competitive base salary, bonus and a generous grant of our valuable early-stage equity. The target base salary for this role is approximately $185,000.00 - $225,000.00. The base salary offered may be slightly higher or lower than the target base salary, based on the final scope as determined by the depth of the experience and skills demonstrated by candidate in the interviews.
We offer great benefits (health, vision, dental and life insurance), collaborative and continuous learning work environment, where you will get a chance to work with smart and dedicated people engaged in developing the next generation architecture for high performance computing.
Celestial AI Inc. is proud to be an equal opportunity workplace and is an affirmative action employer.
#LI-Onsite
Top Skills
What We Do
Celestial AI is a Machine Learning (ML) accelerator company that has developed a proprietary technology platform which enables the next generation of high-performance computing solutions. Celestial AI’s mission is to transform data parallel computing with a proprietary Photonic Fabric™ technology platform which uses light for data movement both within chip and between chips.
Advancements in data communications have driven robust silicon photonics technology and volume manufacturing ecosystems that are ripe for commercial implementation of ML and high-performance computing (HPC) solutions which leverage integrated silicon photonics for data movement.
Celestial AI’s system delivers differentiated single node performance that scales efficiently, providing significant performance gains for multi-node and multi model applications. The scalability of Celestial AI’s accelerator architecture enables an efficient and performant mapping of data and compute over a broad range of ML model types without the need for complex software optimizations. Celestial AI’s competitive advantage will further grow over time as ML models continue to increase in complexity and size.
Celestial AI has assembled a highly experienced team of industry leaders who have a track record of building multiple successful technology businesses. The company’s Orion AI accelerator products serve an addressable market that is projected by Omida to exceed $70 billion in 2025
