Intrinsic→
Deep Learning Intern, Model Optimization at Intrinsic · Mountain…
InternshipOn-siteMountain View, CA$146k–$146k/yr
Skills
pythondeep learning frameworksmodel compressionknowledge distillationquantizationdeep learning model trainingcomputer visiontransformersconvolutional neural networksdata analysisclear reporting
Job Description
Summary: Intrinsic is an AI robotics group at Google aiming to reimagine the potential of industrial robotics. In this internship role, you will focus on optimizing computer vision and deep learning models for industrial deployment, working on techniques to compress models while maintaining accuracy.
Responsibilities:
- Optimize state-of-the-art computer vision and deep learning models for deployment in industrial settings
- Research and apply techniques to compress complex models, making them smaller and faster while maintaining high accuracy
- Implement knowledge distillation and quantization strategies to adapt models for specific hardware constraints
- Design experiments to evaluate performance trade-offs between speed, size, and precision
- Collaborate with the team to integrate optimized models into the production software stack
- Accelerate the deployment of advanced perception capabilities by reducing model latency and memory footprint
- Enable real-time robotic control and decision-making by ensuring complex models run efficiently on constrained edge hardware
- Identify and validate novel optimization methods for machine learning pipelines
Required Qualifications:
- Currently pursuing a PhD or Master's degree in Computer Science, Electrical Engineering, Robotics, or a related technical field
- Experience with Python and major deep learning frameworks (e.g., PyTorch, JAX, or TensorFlow)
- Theoretical understanding and practical experience with model compression techniques, specifically knowledge distillation and quantization
- Experience training and evaluating deep learning models for computer vision tasks (e.g., Transformers, CNNs)
- Ability to analyze experimental data to diagnose performance bottlenecks and report findings clearly
Required Skills: Python, Deep learning frameworks, Model compression, Knowledge distillation, Quantization, Deep learning model training, Computer vision, Transformers, Convolutional neural networks, Data analysis, Clear reporting
Benefits: Bonus, Equity, Benefits
Benefits
Bonus
Equity
Benefits