Data Scientist - Model Optimization

quadric.io
Summary
Join Quadric's data science team and contribute to the optimization of neural networks for their innovative GPNPU architecture. Research, prototype, and validate low-precision techniques to make neural networks leaner and faster. Your analyses will define quantization recipes for the Chimera SDK and influence future hardware features. Design statistically rigorous experiments, build calibration datasets, and perform in-depth error analysis. Collaborate with the compiler team to integrate your findings into SDK flows and reference configurations. Publish internal and external findings, and present results to customers and at industry events. Stay current with academic literature and translate promising ideas into prototypes. This role requires a strong background in ML model optimization and data science.
Requirements
- 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, and statistical calibration
- Fluent in Python, PyTorch or TensorFlow, NumPy/Pandas/SciPy, and data‑viz tools (Matplotlib/Plotly)
- Hands‑on with at least one quantization toolkit (PyTorch FX/PTQ/QAT, TF‑Lite, ONNX‑Runtime, TVM, MLIR Quant)
- Working knowledge of CNNs, Transformers and DNN architectures
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
Benefits
- Provide 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
Share this job:
Similar Remote Jobs
