> Markdown version of [/jobs/ext/2851609-data-scientist-model-optimization](https://www.wearedevelopers.com/jobs/ext/2851609-data-scientist-model-optimization). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Data Scientist - Model Optimization - **Company:** quadric, Inc - **Location:** Burlingame, CA, United States - **Experience:** Expert - **Salary:** $110,000.0 - $270,000.0 - **Contract:** Permanent contract - **Skills:** Python (Programming Language), Machine Learning, NumPy, Tensorflow, SciPy, Pytorch, Pandas, Matplotlib, Low Latency, ONNX (Open Neural Network Exchange) Format, Plotly, Hardware Acceleration - **Published:** September 11, 2026 - **Apply:** https://www.thejobnetwork.com/job/037a2a04-2622-412a-bc77-fba53dfb26e6/data-scientist-model-optimization ## About the Role * M.S./Ph.D. in CS, EE, Applied Math, or similar, with 5+ years in ML model optimization or data-science-driven research. * Deep grasp of fixed-point arithmetic, quantization theory, numerical analysis, and statistical calibration. * Strong ability to implement quantization algorithms from first principles, not just use existing frameworks. * Fluent in Python, PyTorch or TensorFlow, NumPy/Pandas/SciPy, and data-viz tools (Matplotlib/Plotly). * Experience implementing custom quantizers and understanding their interaction with hardware constraints (bit-width, format, operations). * Hands-on with at least one quantization toolkit (PyTorch FX/PTQ/QAT, TF-Lite, ONNX-Runtime, TVM, MLIR Quant) and ability to extend them. * Working knowledge of CNNs, Transformers, and DNN architectures. * Bonus: Experience with custom hardware accelerators, DSPs, or neural processing units. ## Description You will be joining the data science team focused on model optimization for Quadric's custom GPNPU architecture. You will research, prototype, and implement novel quantization algorithms tailored to our hardware constraints. Beyond applying existing techniques, you'll develop custom low-precision methods that maximize performance on the Chimera GPNPU. Your work will directly shape the quantization capabilities in the Chimera SDK and influence future hardware features., This California Bay Area based engineering role is intended to be primarily in-office at our Burlingame location, with the ability to commute regularly. We believe strong technical collaboration, rapid iteration, and shared problem-solving are well supported by working together in person. The team and company also gather periodically for onsite meetings and offsite events to connect, collaborate, and align on priorities., * Design statistically rigorous experiments to compare PTQ, QAT, and mixed-precision schemes on vision, language, and multimodal models. * Implement custom quantization algorithms from scratch, adapting existing techniques or developing novel approaches to match Chimera GPNPU's unique architectural features and numerical formats. * Build calibration datasets; develop Python notebooks/dashboards to track accuracy, latency, power, and memory trade-offs. * Perform layer-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 white papers, 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., By submitting an application, you acknowledge that Quadric will collect and process your personal information as part of the hiring process. Please review our Privacy Policy to understand how we handle your data. ## Related Videos - [Python Data Visualization @ Deepnote (w/ PyViz overview)](https://www.wearedevelopers.com/videos/113-python-data-visualization-deepnote-w-pyviz-overview) - [Vectorize all the things! Using linear algebra and NumPy to make your Python code lightning fast.](https://www.wearedevelopers.com/videos/562-vectorize-all-the-things-using-linear-algebra-and-numpy-to-make-your-python-code-lightning-fast) - [Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated](https://www.wearedevelopers.com/videos/100099-tour-de-force-open-source-llm-inference-optimization-from-simple-to-sophisticated) - [Advanced Typing in TypeScript](https://www.wearedevelopers.com/videos/496-advanced-typing-in-typescript) - [Accelerating Python on GPUs](https://www.wearedevelopers.com/videos/859-accelerating-python-on-gpus) - [Accelerating Python on GPUs](https://www.wearedevelopers.com/videos/1112-accelerating-python-on-gpus) ## Related Articles - [MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production](https://www.wearedevelopers.com/magazine/115-mlops-deploying-maintaining-and-evolving-machine-learning-models-in-production) - [The Best Large Language Models on The Market](https://www.wearedevelopers.com/magazine/319-the-best-large-language-models-on-the-market) - [7 Cloud Computing Trends Coming in 2025 for Developers](https://www.wearedevelopers.com/magazine/412-7-cloud-computing-trends-coming-in-2025-for-developers) - [The Fastest-Growing Tech Sectors to Look Out for in 2025](https://www.wearedevelopers.com/magazine/373-the-fastest-growing-tech-sectors-to-look-out-for-in-2025) - [What’s the latest in NVIDIA CUDA Python](https://www.wearedevelopers.com/magazine/568-what-s-the-latest-in-nvidia-cuda-python) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering)