Data Scientist - Model Optimization

Quadric has created an innovative general purpose neural processing unit (GPNPU) architecture. Quadric's co-optimized software and hardware is targeted to run neural network (NN) inference workloads in a wide variety of edge and endpoint devices, ranging from battery operated smart-sensor systems to high-performance automotive or autonomous vehicle systems. Unlike other NPUs or neural network accelerators in the industry today that can only accelerate a portion 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 be joining the data science team that is focused on model optimization, will research, prototype, and validate low‑precision techniques that make neural networks leaner and faster on the Chimera GPNPU. Your analyses will set the quantization recipes that ship in the Chimera SDK and influence future hardware features.

Responsibilities:

* Design statistically 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 track accuracy, latency, power, and memory trade‑offs.

* Perform layer‑ and token‑level error analysis to guide numerical‐format choices.

* Partner with compiler team to convert your findings into turnkey SDK flows and reference configs.

* Publish internal whitepapers, external benchmarks, and present results to customers and at industry events.

* Monitor academic literature in compression and efficient inference; translate promising ideas into reproducible prototypes.