ML Research Scientist, Prediction & Smart Agents

The role

You will build state-of-the-art models for predicting the behavior of surrounding traffic. This work involves using generative sequence modeling and building smart, controllable agents for closed-loop simulation.

What you will do

• Design and build scalable, machine learning-based prediction systems.
• Conduct research in generative sequence modeling and sequential decision-making.
• Collaborate with the Planning team to design realistic and controllable agents for closed-loop simulation.
• Mitigate accumulated uncertainties across interconnected autonomy components.
• Collaborate across various autonomy teams to develop holistic solutions.
• Derive practical, deployable solutions for real-world vehicles.

Required qualifications

• M.Sc. in Computer Science, Artificial Intelligence, Mathematics, or a closely related field
• Subject matter expertise and research experience in sequential decision-making, prediction, Imitation Learning, Deep Reinforcement Learning, generative modeling, large models (pretraining/finetuning),
• Strong problem solving and programming skills in Python
• 2+ years of deploying machine learning systems onboard, ideally in the area of prediction
• Demonstrated research publications in top conferences (e.g., NeurIPS, ICLR, ICML, CVPR, RSS, CoRL, ICRA, IROS etc.)

Nice to have

• Ph.D. focusing on Computer Science, Artificial Intelligence, Mathematics, or a closely related field
• C++
• Deep background in Embodied AI for robotics
• Causal reasoning
• Model interpretability and explainability
• Joint prediction and planning
• Understanding of Diffusion Models

Benefits

• Annual performance bonus
• Equity
• Competitive benefits package

About the company

Nuro is a physical AI company developing Level 4 autonomous driving technology. The company is building a universal autonomy platform for a wide range of vehicles, use cases, and markets.