quadric.io
Quadric has created an innovative general purpose neural processing unit (GPNPU) architecture. Quadric's co-optimized software and hardware are designed to run neural network (NN) inference workloads across a wide range of edge and endpoint devices, from battery-operated smart sensors to high-performance automotive or autonomous vehicle systems. Unlike other NPUs or neural network accelerators that can only accelerate parts of a machine learning graph, the Quadric GPNPU executes both NN graph code and conventional C++ DSP and control code.
What We Value:
Integrity, Humility, Happiness
What We Expect:
Initiative, Collaboration, Completion
Role:
You will join the data science team focused on model optimization, researching, prototyping, and validating low-precision techniques that make neural networks more efficient on the ChimeraGPNPU. Your analyses will establish quantization recipes for the ChimeraSDK and influence future hardware features. Responsibilities:
Design rigorous experiments to compare PTQ, QAT, pruning, and mixed-precision schemes on vision, language, and multimodal models. Build calibration datasets; develop Python notebooks/dashboards to monitor accuracy, latency, power, and memory trade-offs. Perform layer- and token-level error analysis to guide numerical format choices. Collaborate with the compiler team to turn findings into SDK flows and reference configurations. Publish internal whitepapers, external benchmarks, and present results at industry events. Stay updated with academic literature on compression and efficient inference; translate promising ideas into prototypes. M.S./Ph.D. in CS, EE, Applied Math, or similar, with 5+ years in ML model optimization or data-driven research. Deep understanding of fixed-point arithmetic, quantization theory, and statistical calibration. Proficiency in Python, PyTorch or TensorFlow, NumPy/Pandas/SciPy, and data visualization tools (Matplotlib/Plotly). Experience with at least one quantization toolkit (PyTorchFX/PTQ/QAT, TF-Lite, ONNX-Runtime, TVM, MLIRQuant). Knowledge of CNNs, Transformers, and DNN architectures. Competitive salaries and meaningful equity. Health Care Plan (Medical, Dental & Vision). Retirement Plan (401k, IRA). Life Insurance (Basic, Voluntary & AD&D). Paid Time Off (Vacation, Sick & Public Holidays). Family Leave (Maternity, Paternity). Work From Home. Free Food & Snacks. Founded in 2016 and based in downtown Burlingame, California, Quadric is building the worlds first supercomputer designed for the real-time needs of edge devices. Quadric aims to empower developers across industries with superpowers to create tomorrows technology today. The company was co-founded by technologists from MIT and Carnegie Mellon, previously the technical co-founders of Bitcoin computing company 21. Quadric is proud to be an equal opportunity workplace and an affirmative action employer. We are committed to equal employment opportunity regardless of race, religion, sex, national origin, sexual orientation, age, citizenship, marital status, or disability.
#J-18808-Ljbffr
You will join the data science team focused on model optimization, researching, prototyping, and validating low-precision techniques that make neural networks more efficient on the ChimeraGPNPU. Your analyses will establish quantization recipes for the ChimeraSDK and influence future hardware features. Responsibilities:
Design rigorous experiments to compare PTQ, QAT, pruning, and mixed-precision schemes on vision, language, and multimodal models. Build calibration datasets; develop Python notebooks/dashboards to monitor accuracy, latency, power, and memory trade-offs. Perform layer- and token-level error analysis to guide numerical format choices. Collaborate with the compiler team to turn findings into SDK flows and reference configurations. Publish internal whitepapers, external benchmarks, and present results at industry events. Stay updated with academic literature on compression and efficient inference; translate promising ideas into prototypes. M.S./Ph.D. in CS, EE, Applied Math, or similar, with 5+ years in ML model optimization or data-driven research. Deep understanding of fixed-point arithmetic, quantization theory, and statistical calibration. Proficiency in Python, PyTorch or TensorFlow, NumPy/Pandas/SciPy, and data visualization tools (Matplotlib/Plotly). Experience with at least one quantization toolkit (PyTorchFX/PTQ/QAT, TF-Lite, ONNX-Runtime, TVM, MLIRQuant). Knowledge of CNNs, Transformers, and DNN architectures. Competitive salaries and meaningful equity. Health Care Plan (Medical, Dental & Vision). Retirement Plan (401k, IRA). Life Insurance (Basic, Voluntary & AD&D). Paid Time Off (Vacation, Sick & Public Holidays). Family Leave (Maternity, Paternity). Work From Home. Free Food & Snacks. Founded in 2016 and based in downtown Burlingame, California, Quadric is building the worlds first supercomputer designed for the real-time needs of edge devices. Quadric aims to empower developers across industries with superpowers to create tomorrows technology today. The company was co-founded by technologists from MIT and Carnegie Mellon, previously the technical co-founders of Bitcoin computing company 21. Quadric is proud to be an equal opportunity workplace and an affirmative action employer. We are committed to equal employment opportunity regardless of race, religion, sex, national origin, sexual orientation, age, citizenship, marital status, or disability.
#J-18808-Ljbffr